[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-stickerdaniel--linkedin-mcp-server":3,"tool-stickerdaniel--linkedin-mcp-server":61},[4,18,26,36,44,53],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":17},4358,"openclaw","openclaw\u002Fopenclaw","OpenClaw 是一款专为个人打造的本地化 AI 助手，旨在让你在自己的设备上拥有完全可控的智能伙伴。它打破了传统 AI 助手局限于特定网页或应用的束缚，能够直接接入你日常使用的各类通讯渠道，包括微信、WhatsApp、Telegram、Discord、iMessage 等数十种平台。无论你在哪个聊天软件中发送消息，OpenClaw 都能即时响应，甚至支持在 macOS、iOS 和 Android 设备上进行语音交互，并提供实时的画布渲染功能供你操控。\n\n这款工具主要解决了用户对数据隐私、响应速度以及“始终在线”体验的需求。通过将 AI 部署在本地，用户无需依赖云端服务即可享受快速、私密的智能辅助，真正实现了“你的数据，你做主”。其独特的技术亮点在于强大的网关架构，将控制平面与核心助手分离，确保跨平台通信的流畅性与扩展性。\n\nOpenClaw 非常适合希望构建个性化工作流的技术爱好者、开发者，以及注重隐私保护且不愿被单一生态绑定的普通用户。只要具备基础的终端操作能力（支持 macOS、Linux 及 Windows WSL2），即可通过简单的命令行引导完成部署。如果你渴望拥有一个懂你",349277,3,"2026-04-06T06:32:30",[13,14,15,16],"Agent","开发框架","图像","数据工具","ready",{"id":19,"name":20,"github_repo":21,"description_zh":22,"stars":23,"difficulty_score":10,"last_commit_at":24,"category_tags":25,"status":17},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,"2026-04-05T11:01:52",[14,15,13],{"id":27,"name":28,"github_repo":29,"description_zh":30,"stars":31,"difficulty_score":32,"last_commit_at":33,"category_tags":34,"status":17},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",144730,2,"2026-04-07T23:26:32",[14,13,35],"语言模型",{"id":37,"name":38,"github_repo":39,"description_zh":40,"stars":41,"difficulty_score":32,"last_commit_at":42,"category_tags":43,"status":17},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",107888,"2026-04-06T11:32:50",[14,15,13],{"id":45,"name":46,"github_repo":47,"description_zh":48,"stars":49,"difficulty_score":32,"last_commit_at":50,"category_tags":51,"status":17},4721,"markitdown","microsoft\u002Fmarkitdown","MarkItDown 是一款由微软 AutoGen 团队打造的轻量级 Python 工具，专为将各类文件高效转换为 Markdown 格式而设计。它支持 PDF、Word、Excel、PPT、图片（含 OCR）、音频（含语音转录）、HTML 乃至 YouTube 链接等多种格式的解析，能够精准提取文档中的标题、列表、表格和链接等关键结构信息。\n\n在人工智能应用日益普及的今天，大语言模型（LLM）虽擅长处理文本，却难以直接读取复杂的二进制办公文档。MarkItDown 恰好解决了这一痛点，它将非结构化或半结构化的文件转化为模型“原生理解”且 Token 效率极高的 Markdown 格式，成为连接本地文件与 AI 分析 pipeline 的理想桥梁。此外，它还提供了 MCP（模型上下文协议）服务器，可无缝集成到 Claude Desktop 等 LLM 应用中。\n\n这款工具特别适合开发者、数据科学家及 AI 研究人员使用，尤其是那些需要构建文档检索增强生成（RAG）系统、进行批量文本分析或希望让 AI 助手直接“阅读”本地文件的用户。虽然生成的内容也具备一定可读性，但其核心优势在于为机器",93400,"2026-04-06T19:52:38",[52,14],"插件",{"id":54,"name":55,"github_repo":56,"description_zh":57,"stars":58,"difficulty_score":10,"last_commit_at":59,"category_tags":60,"status":17},4487,"LLMs-from-scratch","rasbt\u002FLLMs-from-scratch","LLMs-from-scratch 是一个基于 PyTorch 的开源教育项目，旨在引导用户从零开始一步步构建一个类似 ChatGPT 的大型语言模型（LLM）。它不仅是同名技术著作的官方代码库，更提供了一套完整的实践方案，涵盖模型开发、预训练及微调的全过程。\n\n该项目主要解决了大模型领域“黑盒化”的学习痛点。许多开发者虽能调用现成模型，却难以深入理解其内部架构与训练机制。通过亲手编写每一行核心代码，用户能够透彻掌握 Transformer 架构、注意力机制等关键原理，从而真正理解大模型是如何“思考”的。此外，项目还包含了加载大型预训练权重进行微调的代码，帮助用户将理论知识延伸至实际应用。\n\nLLMs-from-scratch 特别适合希望深入底层原理的 AI 开发者、研究人员以及计算机专业的学生。对于不满足于仅使用 API，而是渴望探究模型构建细节的技术人员而言，这是极佳的学习资源。其独特的技术亮点在于“循序渐进”的教学设计：将复杂的系统工程拆解为清晰的步骤，配合详细的图表与示例，让构建一个虽小但功能完备的大模型变得触手可及。无论你是想夯实理论基础，还是为未来研发更大规模的模型做准备",90106,"2026-04-06T11:19:32",[35,15,13,14],{"id":62,"github_repo":63,"name":64,"description_en":65,"description_zh":66,"ai_summary_zh":67,"readme_en":68,"readme_zh":69,"quickstart_zh":70,"use_case_zh":71,"hero_image_url":72,"owner_login":73,"owner_name":74,"owner_avatar_url":75,"owner_bio":76,"owner_company":77,"owner_location":78,"owner_email":77,"owner_twitter":77,"owner_website":79,"owner_url":80,"languages":81,"stars":90,"forks":91,"last_commit_at":92,"license":93,"difficulty_score":32,"env_os":94,"env_gpu":95,"env_ram":95,"env_deps":96,"category_tags":103,"github_topics":104,"view_count":32,"oss_zip_url":77,"oss_zip_packed_at":77,"status":17,"created_at":124,"updated_at":125,"faqs":126,"releases":156},5349,"stickerdaniel\u002Flinkedin-mcp-server","linkedin-mcp-server","Open-source MCP server for LinkedIn. Give Claude and any MCP-compatible AI assistant access to profiles, companies, jobs, and messages.","linkedin-mcp-server 是一款开源工具，旨在让 Claude 等支持 MCP 协议的 AI 助手直接连接并操作你的 LinkedIn 账户。通过它，AI 可以读取个人档案、查询公司信息、搜索职位详情，甚至管理站内消息和发送好友请求，将原本需要人工浏览的社交网络数据转化为可被 AI 调用的结构化信息。\n\n这款工具主要解决了 AI 无法直接访问实时、私有社交数据的痛点。以往用户需手动复制粘贴大量背景资料才能让 AI 进行分析，现在只需提供链接或指令，AI 即可自动获取候选人的详细履历、合作伙伴的公司动态，或是针对特定职位描述优化简历，极大提升了招聘调研、商务拓展及职业规划的效率。\n\n它非常适合招聘人员、销售专家、求职者以及希望构建自动化工作流的开发者使用。对于普通职场人士，它也能作为智能助理辅助日常人脉维护。技术层面，linkedin-mcp-server 基于 MCP（Model Context Protocol）标准构建，支持多种便捷部署方式（如 uvx、Docker 及 Claude 桌面端插件），并提供了细粒度的功能控制，例如允许用户指定仅读取档案中的“教育经历”或","linkedin-mcp-server 是一款开源工具，旨在让 Claude 等支持 MCP 协议的 AI 助手直接连接并操作你的 LinkedIn 账户。通过它，AI 可以读取个人档案、查询公司信息、搜索职位详情，甚至管理站内消息和发送好友请求，将原本需要人工浏览的社交网络数据转化为可被 AI 调用的结构化信息。\n\n这款工具主要解决了 AI 无法直接访问实时、私有社交数据的痛点。以往用户需手动复制粘贴大量背景资料才能让 AI 进行分析，现在只需提供链接或指令，AI 即可自动获取候选人的详细履历、合作伙伴的公司动态，或是针对特定职位描述优化简历，极大提升了招聘调研、商务拓展及职业规划的效率。\n\n它非常适合招聘人员、销售专家、求职者以及希望构建自动化工作流的开发者使用。对于普通职场人士，它也能作为智能助理辅助日常人脉维护。技术层面，linkedin-mcp-server 基于 MCP（Model Context Protocol）标准构建，支持多种便捷部署方式（如 uvx、Docker 及 Claude 桌面端插件），并提供了细粒度的功能控制，例如允许用户指定仅读取档案中的“教育经历”或“项目经验”部分，在提升灵活性的同时也兼顾了数据隐私与安全。","# LinkedIn MCP Server\n\n\u003Cp align=\"left\">\n  \u003Ca href=\"https:\u002F\u002Fpypi.org\u002Fproject\u002Flinkedin-scraper-mcp\u002F\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Flinkedin-scraper-mcp?color=blue\" alt=\"PyPI\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Factions\u002Fworkflows\u002Fci.yml\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Factions\u002Fworkflows\u002Fci.yml\u002Fbadge.svg?branch=main\" alt=\"CI Status\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Factions\u002Fworkflows\u002Frelease.yml\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Factions\u002Fworkflows\u002Frelease.yml\u002Fbadge.svg?branch=main\" alt=\"Release\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fblob\u002Fmain\u002FLICENSE\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-Apache%202.0-%233fb950?labelColor=32383f\" alt=\"License\">\u003C\u002Fa>\n\u003C\u002Fp>\n\nThrough this LinkedIn MCP server, AI assistants like Claude can connect to your LinkedIn. Access profiles and companies, search for jobs, or get job details.\n\n## Installation Methods\n\n[![uvx](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fuvx-Quick_Install-de5fe9?style=for-the-badge&logo=data:image\u002Fsvg+xml;base64,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)](#-uvx-setup-recommended---universal)\n[![Install MCP Bundle](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FClaude_Desktop_MCPB-d97757?style=for-the-badge&logo=anthropic)](#-claude-desktop-mcp-bundle-formerly-dxt)\n[![Docker](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDocker-Universal_MCP-008fe2?style=for-the-badge&logo=docker&logoColor=008fe2)](#-docker-setup)\n[![Development](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDevelopment-Local-ffdc53?style=for-the-badge&logo=python&logoColor=ffdc53)](#-local-setup-develop--contribute)\n\n\u003Chttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Feb84419a-6eaf-47bd-ac52-37bc59c83680>\n\n## Usage Examples\n\n```\nResearch the background of this candidate https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fstickerdaniel\u002F\n```\n\n```\nGet this company profile for partnership discussions https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002Finframs\u002F\n```\n\n```\nSuggest improvements for my CV to target this job posting https:\u002F\u002Fwww.linkedin.com\u002Fjobs\u002Fview\u002F4252026496\n```\n\n```\nWhat has Anthropic been posting about recently? https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002Fanthropicresearch\u002F\n```\n\n## Features & Tool Status\n\n| Tool | Description | Status |\n|------|-------------|--------|\n| `get_person_profile` | Get profile info with explicit section selection (experience, education, interests, honors, languages, certifications, contact_info, posts) | working |\n| `connect_with_person` | Send a connection request or accept an incoming one, with optional note | [#304](https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fissues\u002F304) |\n| `get_sidebar_profiles` | Extract profile URLs from sidebar recommendation sections (\"More profiles for you\", \"Explore premium profiles\", \"People you may know\") on a profile page | working |\n| `get_inbox` | List recent conversations from the LinkedIn messaging inbox | working |\n| `get_conversation` | Read a specific messaging conversation by username or thread ID | [#307](https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fissues\u002F307) |\n| `search_conversations` | Search messages by keyword | working |\n| `send_message` | Send a message to a LinkedIn user (requires confirmation) | working |\n| `get_company_profile` | Extract company information with explicit section selection (posts, jobs) | working |\n| `get_company_posts` | Get recent posts from a company's LinkedIn feed | working |\n| `search_jobs` | Search for jobs with keywords and location filters | working |\n| `search_people` | Search for people by keywords and location | working |\n| `get_job_details` | Get detailed information about a specific job posting | working |\n| `close_session` | Close browser session and clean up resources | working |\n\n> [!IMPORTANT]\n> **Breaking change:** LinkedIn recently made some changes to prevent scraping. The newest version uses [Patchright](https:\u002F\u002Fgithub.com\u002FKaliiiiiiiiii-Vinyzu\u002Fpatchright-python) with persistent browser profiles instead of Playwright with session files. Old `session.json` files and `LINKEDIN_COOKIE` env vars are no longer supported. Run `--login` again to create a new profile + cookie file that can be mounted in docker. 02\u002F2026\n\n\u003Cbr\u002F>\n\u003Cbr\u002F>\n\n## 🚀 uvx Setup (Recommended - Universal)\n\n**Prerequisites:** [Install uv](https:\u002F\u002Fdocs.astral.sh\u002Fuv\u002Fgetting-started\u002Finstallation\u002F).\n\n### Installation\n\n**Client Configuration**\n\n```json\n{\n  \"mcpServers\": {\n    \"linkedin\": {\n      \"command\": \"uvx\",\n      \"args\": [\"linkedin-scraper-mcp@latest\"],\n      \"env\": { \"UV_HTTP_TIMEOUT\": \"300\" }\n    }\n  }\n}\n```\n\nThe `@latest` tag ensures you always run the newest version — `uvx` checks PyPI on each client launch and updates automatically. The server starts quickly, prepares the shared Patchright Chromium browser cache in the background under `~\u002F.linkedin-mcp\u002Fpatchright-browsers`, and opens a LinkedIn login browser window on the first tool call that needs authentication.\n\n> [!NOTE]\n> Early tool calls may return a setup\u002Fauthentication-in-progress error until browser setup or login finishes. If you prefer to create a session explicitly, run `uvx linkedin-scraper-mcp@latest --login`.\n\n### uvx Setup Help\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>🔧 Configuration\u003C\u002Fb>\u003C\u002Fsummary>\n\n**Transport Modes:**\n\n- **Default (stdio)**: Standard communication for local MCP servers\n- **Streamable HTTP**: For web-based MCP server\n- If no transport is specified, the server defaults to `stdio`\n- An interactive terminal without explicit transport shows a chooser prompt\n\n**CLI Options:**\n\n- `--login` - Open browser to log in and save persistent profile\n- `--no-headless` - Show browser window (useful for debugging scraping issues)\n- `--log-level {DEBUG,INFO,WARNING,ERROR}` - Set logging level (default: WARNING)\n- `--transport {stdio,streamable-http}` - Optional: force transport mode (default: stdio)\n- `--host HOST` - HTTP server host (default: 127.0.0.1)\n- `--port PORT` - HTTP server port (default: 8000)\n- `--path PATH` - HTTP server path (default: \u002Fmcp)\n- `--logout` - Clear stored LinkedIn browser profile\n- `--timeout MS` - Browser timeout for page operations in milliseconds (default: 5000)\n- `--user-data-dir PATH` - Path to persistent browser profile directory (default: ~\u002F.linkedin-mcp\u002Fprofile)\n- `--chrome-path PATH` - Path to Chrome\u002FChromium executable (for custom browser installations)\n\n**Basic Usage Examples:**\n\n```bash\n# Run with debug logging\nuvx linkedin-scraper-mcp@latest --log-level DEBUG\n```\n\n**HTTP Mode Example (for web-based MCP clients):**\n\n```bash\nuvx linkedin-scraper-mcp@latest --transport streamable-http --host 127.0.0.1 --port 8080 --path \u002Fmcp\n```\n\nRuntime server logs are emitted by FastMCP\u002FUvicorn.\n\nTool calls are serialized within a single server process to protect the shared\nLinkedIn browser session. Concurrent client requests queue instead of running in\nparallel. Use `--log-level DEBUG` to see scraper lock wait\u002Facquire\u002Frelease logs.\n\n**Test with mcp inspector:**\n\n1. Install and run mcp inspector ```bunx @modelcontextprotocol\u002Finspector```\n2. Click pre-filled token url to open the inspector in your browser\n3. Select `Streamable HTTP` as `Transport Type`\n4. Set `URL` to `http:\u002F\u002Flocalhost:8080\u002Fmcp`\n5. Connect\n6. Test tools\n\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>❗ Troubleshooting\u003C\u002Fb>\u003C\u002Fsummary>\n\n**Installation issues:**\n\n- Ensure you have uv installed: `curl -LsSf https:\u002F\u002Fastral.sh\u002Fuv\u002Finstall.sh | sh`\n- Check uv version: `uv --version` (should be 0.4.0 or higher)\n- On first run, `uvx` downloads all Python dependencies. On slow connections, uv's default 30s HTTP timeout may be too short. The recommended config above already sets `UV_HTTP_TIMEOUT=300` (seconds) to avoid this.\n\n**Session issues:**\n\n- Browser profile is stored at `~\u002F.linkedin-mcp\u002Fprofile\u002F`\n- Managed browser downloads are cached at `~\u002F.linkedin-mcp\u002Fpatchright-browsers\u002F`\n- Make sure you have only one active LinkedIn session at a time\n\n**Login issues:**\n\n- LinkedIn may require a login confirmation in the LinkedIn mobile app for `--login`\n- You might get a captcha challenge if you logged in frequently. Run `uvx linkedin-scraper-mcp@latest --login` which opens a browser where you can solve it manually.\n\n**Timeout issues:**\n\n- If pages fail to load or elements aren't found, try increasing the timeout: `--timeout 10000`\n- Users on slow connections may need higher values (e.g., 15000-30000ms)\n- Can also set via environment variable: `TIMEOUT=10000`\n\n**Custom Chrome path:**\n\n- If Chrome is installed in a non-standard location, use `--chrome-path \u002Fpath\u002Fto\u002Fchrome`\n- Can also set via environment variable: `CHROME_PATH=\u002Fpath\u002Fto\u002Fchrome`\n\n\u003C\u002Fdetails>\n\n\u003Cbr\u002F>\n\u003Cbr\u002F>\n\n## 📦 Claude Desktop MCP Bundle (formerly DXT)\n\n**Prerequisites:** [Claude Desktop](https:\u002F\u002Fclaude.ai\u002Fdownload).\n\n**One-click installation** for Claude Desktop users:\n\n1. Download the latest `.mcpb` artifact from [releases](https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Freleases\u002Flatest)\n2. Click the downloaded `.mcpb` file to install it into Claude Desktop\n3. Call any LinkedIn tool\n\nOn startup, the MCP Bundle starts preparing the shared Patchright Chromium browser cache in the background. If you call a tool too early, Claude will surface a setup-in-progress error. On the first tool call that needs authentication, the server opens a LinkedIn login browser window and asks you to retry after sign-in.\n\n### MCP Bundle Setup Help\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>❗ Troubleshooting\u003C\u002Fb>\u003C\u002Fsummary>\n\n**First-time setup behavior:**\n\n- Claude Desktop starts the bundle immediately; browser setup continues in the background\n- If the Patchright Chromium browser is still downloading, retry the tool after a short wait\n- Managed browser downloads are shared under `~\u002F.linkedin-mcp\u002Fpatchright-browsers\u002F`\n\n**Login issues:**\n\n- Make sure you have only one active LinkedIn session at a time\n- LinkedIn may require a login confirmation in the LinkedIn mobile app for `--login`\n- You might get a captcha challenge if you logged in frequently. Run `uvx linkedin-scraper-mcp@latest --login` which opens a browser where you can solve captchas manually. See the [uvx setup](#-uvx-setup-recommended---universal) for prerequisites.\n\n**Timeout issues:**\n\n- If pages fail to load or elements aren't found, try increasing the timeout: `--timeout 10000`\n- Users on slow connections may need higher values (e.g., 15000-30000ms)\n- Can also set via environment variable: `TIMEOUT=10000`\n\n\u003C\u002Fdetails>\n\n\u003Cbr\u002F>\n\u003Cbr\u002F>\n\n## 🐳 Docker Setup\n\n**Prerequisites:** Make sure you have [Docker](https:\u002F\u002Fwww.docker.com\u002Fget-started\u002F) installed and running, and [uv](https:\u002F\u002Fdocs.astral.sh\u002Fuv\u002Fgetting-started\u002Finstallation\u002F) installed on the host for the one-time `--login` step.\n\n### Authentication\n\nDocker runs headless (no browser window), so you need to create a browser profile locally first and mount it into the container.\n\n**Step 1: Create profile on the host (one-time setup)**\n\n```bash\nuvx linkedin-scraper-mcp@latest --login\n```\n\nThis opens a browser window where you log in manually (5 minute timeout for 2FA, captcha, etc.). The browser profile and cookies are saved under `~\u002F.linkedin-mcp\u002F`. On startup, Docker derives a Linux browser profile from your host cookies and creates a fresh session each time. If you experience stability issues with Docker, consider using the [uvx setup](#-uvx-setup-recommended---universal) instead.\n\n**Step 2: Configure Claude Desktop with Docker**\n\n```json\n{\n  \"mcpServers\": {\n    \"linkedin\": {\n      \"command\": \"docker\",\n      \"args\": [\n        \"run\", \"--rm\", \"-i\",\n        \"-v\", \"~\u002F.linkedin-mcp:\u002Fhome\u002Fpwuser\u002F.linkedin-mcp\",\n        \"stickerdaniel\u002Flinkedin-mcp-server:latest\"\n      ]\n    }\n  }\n}\n```\n\n> [!NOTE]\n> Docker creates a fresh session on each startup. Sessions may expire over time — run `uvx linkedin-scraper-mcp@latest --login` again if you encounter authentication issues.\n\n> [!NOTE]\n> **Why can't I run `--login` in Docker?** Docker containers don't have a display server. Create a profile on your host using the [uvx setup](#-uvx-setup-recommended---universal) and mount it into Docker.\n\n### Docker Setup Help\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>🔧 Configuration\u003C\u002Fb>\u003C\u002Fsummary>\n\n**Transport Modes:**\n\n- **Default (stdio)**: Standard communication for local MCP servers\n- **Streamable HTTP**: For a web-based MCP server\n- If no transport is specified, the server defaults to `stdio`\n- An interactive terminal without explicit transport shows a chooser prompt\n\n**CLI Options:**\n\n- `--log-level {DEBUG,INFO,WARNING,ERROR}` - Set logging level (default: WARNING)\n- `--transport {stdio,streamable-http}` - Optional: force transport mode (default: stdio)\n- `--host HOST` - HTTP server host (default: 127.0.0.1)\n- `--port PORT` - HTTP server port (default: 8000)\n- `--path PATH` - HTTP server path (default: \u002Fmcp)\n- `--logout` - Clear all stored LinkedIn auth state, including source and derived runtime profiles\n- `--timeout MS` - Browser timeout for page operations in milliseconds (default: 5000)\n- `--user-data-dir PATH` - Path to persistent browser profile directory (default: ~\u002F.linkedin-mcp\u002Fprofile)\n- `--chrome-path PATH` - Path to Chrome\u002FChromium executable (rarely needed in Docker)\n\n> [!NOTE]\n> `--login` and `--no-headless` are not available in Docker (no display server). Use the [uvx setup](#-uvx-setup-recommended---universal) to create profiles.\n\n**HTTP Mode Example (for web-based MCP clients):**\n\n```bash\ndocker run -it --rm \\\n  -v ~\u002F.linkedin-mcp:\u002Fhome\u002Fpwuser\u002F.linkedin-mcp \\\n  -p 8080:8080 \\\n  stickerdaniel\u002Flinkedin-mcp-server:latest \\\n  --transport streamable-http --host 0.0.0.0 --port 8080 --path \u002Fmcp\n```\n\nRuntime server logs are emitted by FastMCP\u002FUvicorn.\n\n**Test with mcp inspector:**\n\n1. Install and run mcp inspector ```bunx @modelcontextprotocol\u002Finspector```\n2. Click pre-filled token url to open the inspector in your browser\n3. Select `Streamable HTTP` as `Transport Type`\n4. Set `URL` to `http:\u002F\u002Flocalhost:8080\u002Fmcp`\n5. Connect\n6. Test tools\n\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>❗ Troubleshooting\u003C\u002Fb>\u003C\u002Fsummary>\n\n**Docker issues:**\n\n- Make sure [Docker](https:\u002F\u002Fwww.docker.com\u002Fget-started\u002F) is installed\n- Check if Docker is running: `docker ps`\n\n**Login issues:**\n\n- Make sure you have only one active LinkedIn session at a time\n- LinkedIn may require a login confirmation in the LinkedIn mobile app for `--login`\n- You might get a captcha challenge if you logged in frequently. Run `uvx linkedin-scraper-mcp@latest --login` which opens a browser where you can solve captchas manually. See the [uvx setup](#-uvx-setup-recommended---universal) for prerequisites.\n- If Docker auth becomes stale after you re-login on the host, restart Docker once so it can fresh-bridge from the new source session generation.\n\n**Timeout issues:**\n\n- If pages fail to load or elements aren't found, try increasing the timeout: `--timeout 10000`\n- Users on slow connections may need higher values (e.g., 15000-30000ms)\n- Can also set via environment variable: `TIMEOUT=10000`\n\n**Custom Chrome path:**\n\n- If Chrome is installed in a non-standard location, use `--chrome-path \u002Fpath\u002Fto\u002Fchrome`\n- Can also set via environment variable: `CHROME_PATH=\u002Fpath\u002Fto\u002Fchrome`\n\n\u003C\u002Fdetails>\n\n\u003Cbr\u002F>\n\u003Cbr\u002F>\n\n## 🐍 Local Setup (Develop & Contribute)\n\nContributions are welcome! See [CONTRIBUTING.md](CONTRIBUTING.md) for architecture guidelines and checklists. Please [open an issue](https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fissues) first to discuss the feature or bug fix before submitting a PR.\n\n**Prerequisites:** [Git](https:\u002F\u002Fgit-scm.com\u002Fdownloads) and [uv](https:\u002F\u002Fdocs.astral.sh\u002Fuv\u002F) installed\n\n### Installation\n\n```bash\n# 1. Clone repository\ngit clone https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\ncd linkedin-mcp-server\n\n# 2. Install UV package manager (if not already installed)\ncurl -LsSf https:\u002F\u002Fastral.sh\u002Fuv\u002Finstall.sh | sh\n\n# 3. Install dependencies\nuv sync\nuv sync --group dev\n\n# 4. Install pre-commit hooks\nuv run pre-commit install\n\n# 5. Start the server\nuv run -m linkedin_mcp_server\n```\n\nThe local server uses the same managed-runtime flow as MCPB and `uvx`: it prepares the Patchright Chromium browser cache in the background and opens LinkedIn login on the first auth-requiring tool call. You can still run `uv run -m linkedin_mcp_server --login` when you want to create the session explicitly.\n\n### Local Setup Help\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>🔧 Configuration\u003C\u002Fb>\u003C\u002Fsummary>\n\n**CLI Options:**\n\n- `--login` - Open browser to log in and save persistent profile\n- `--no-headless` - Show browser window (useful for debugging scraping issues)\n- `--log-level {DEBUG,INFO,WARNING,ERROR}` - Set logging level (default: WARNING)\n- `--transport {stdio,streamable-http}` - Optional: force transport mode (default: stdio)\n- `--host HOST` - HTTP server host (default: 127.0.0.1)\n- `--port PORT` - HTTP server port (default: 8000)\n- `--path PATH` - HTTP server path (default: \u002Fmcp)\n- `--logout` - Clear stored LinkedIn browser profile\n- `--timeout MS` - Browser timeout for page operations in milliseconds (default: 5000)\n- `--status` - Check if current session is valid and exit\n- `--user-data-dir PATH` - Path to persistent browser profile directory (default: ~\u002F.linkedin-mcp\u002Fprofile)\n- `--slow-mo MS` - Delay between browser actions in milliseconds (default: 0, useful for debugging)\n- `--user-agent STRING` - Custom browser user agent\n- `--viewport WxH` - Browser viewport size (default: 1280x720)\n- `--chrome-path PATH` - Path to Chrome\u002FChromium executable (for custom browser installations)\n- `--help` - Show help\n\n> **Note:** Most CLI options have environment variable equivalents. See `.env.example` for details.\n\n**HTTP Mode Example (for web-based MCP clients):**\n\n```bash\nuv run -m linkedin_mcp_server --transport streamable-http --host 127.0.0.1 --port 8000 --path \u002Fmcp\n```\n\n**Claude Desktop:**\n\n```json\n{\n  \"mcpServers\": {\n    \"linkedin\": {\n      \"command\": \"uv\",\n      \"args\": [\"--directory\", \"\u002Fpath\u002Fto\u002Flinkedin-mcp-server\", \"run\", \"-m\", \"linkedin_mcp_server\"]\n    }\n  }\n}\n```\n\n`stdio` is used by default for this config.\n\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>❗ Troubleshooting\u003C\u002Fb>\u003C\u002Fsummary>\n\n**Login issues:**\n\n- Make sure you have only one active LinkedIn session at a time\n- LinkedIn may require a login confirmation in the LinkedIn mobile app for `--login`\n- You might get a captcha challenge if you logged in frequently. The `--login` command opens a browser where you can solve it manually.\n\n**Scraping issues:**\n\n- Use `--no-headless` to see browser actions and debug scraping problems\n- Add `--log-level DEBUG` to see more detailed logging\n\n**Session issues:**\n\n- Browser profile is stored at `~\u002F.linkedin-mcp\u002Fprofile\u002F`\n- Use `--logout` to clear the profile and start fresh\n\n**Python\u002FPatchright issues:**\n\n- Check Python version: `python --version` (should be 3.12+)\n- Reinstall Patchright: `uv run patchright install chromium`\n- Reinstall dependencies: `uv sync --reinstall`\n\n**Timeout issues:**\n\n- If pages fail to load or elements aren't found, try increasing the timeout: `--timeout 10000`\n- Users on slow connections may need higher values (e.g., 15000-30000ms)\n- Can also set via environment variable: `TIMEOUT=10000`\n\n**Custom Chrome path:**\n\n- If Chrome is installed in a non-standard location, use `--chrome-path \u002Fpath\u002Fto\u002Fchrome`\n- Can also set via environment variable: `CHROME_PATH=\u002Fpath\u002Fto\u002Fchrome`\n\n\u003C\u002Fdetails>\n\n\n\u003Cbr\u002F>\n\u003Cbr\u002F>\n\n## Acknowledgements\n\nBuilt with [FastMCP](https:\u002F\u002Fgofastmcp.com\u002F) and [Patchright](https:\u002F\u002Fgithub.com\u002FKaliiiiiiiiii-Vinyzu\u002Fpatchright-python).\n\nUse in accordance with [LinkedIn's Terms of Service](https:\u002F\u002Fwww.linkedin.com\u002Flegal\u002Fuser-agreement). Web scraping may violate LinkedIn's terms. This tool is for personal use only.\n\n## License\n\nThis project is licensed under the Apache 2.0 license.\n\n\u003Cbr>\n","# LinkedIn MCP 服务器\n\n\u003Cp align=\"left\">\n  \u003Ca href=\"https:\u002F\u002Fpypi.org\u002Fproject\u002Flinkedin-scraper-mcp\u002F\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Flinkedin-scraper-mcp?color=blue\" alt=\"PyPI\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Factions\u002Fworkflows\u002Fci.yml\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Factions\u002Fworkflows\u002Fci.yml\u002Fbadge.svg?branch=main\" alt=\"CI 状态\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Factions\u002Fworkflows\u002Frelease.yml\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Factions\u002Fworkflows\u002Frelease.yml\u002Fbadge.svg?branch=main\" alt=\"发布\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fblob\u002Fmain\u002FLICENSE\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-Apache%202.0-%233fb950?labelColor=32383f\" alt=\"许可证\">\u003C\u002Fa>\n\u003C\u002Fp>\n\n通过此 LinkedIn MCP 服务器，Claude 等 AI 助手可以连接到您的 LinkedIn 账户。访问个人资料和公司信息、搜索职位或获取职位详情。\n\n## 安装方法\n\n[![uvx](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fuvx-Quick_Install-de5fe9?style=for-the-badge&logo=data:image\u002Fsvg+xml;base64,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.0Nzc0IDI1Ljk9OThMMTguMzk5OCAyNSL.j998TLE8L.4774g16.032TLE8L.3998g0.0910593TC-5.28619e-06 0.168629L\">uvx 快速安装\u003C\u002Fa>]\n[![安装 MCP 套件](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FClaude_Desktop_MCPB-d97757?style=for-the-badge&logo=anthropic)](#-claude-desktop-mcp-bundle-formerly-dxt)\n[![Docker](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDocker-Universal_MCP-008fe2?style=for-the-badge&logo=docker&logoColor=008fe2)](#-docker-setup)\n[![开发](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDevelopment-Local-ffdc53?style=for-the-badge&logo=python&logoColor=ffdc53)](#-local-setup-develop--contribute)\n\n\u003Chttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Feb84419a-6eaf-47bd-ac52-37bc59c83680>\n\n## 使用示例\n\n```\n研究这位候选人的背景：https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fstickerdaniel\u002F\n```\n\n```\n获取这家公司的简介，用于洽谈合作：https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002Finframs\u002F\n```\n\n```\n为我的简历提出改进建议，以匹配这个职位：https:\u002F\u002Fwww.linkedin.com\u002Fjobs\u002Fview\u002F4252026496\n```\n\n```\nAnthropic 最近在 LinkedIn 上发布了哪些内容？https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002Fanthropicresearch\u002F\n```\n\n## 功能与工具状态\n\n| 工具 | 描述 | 状态 |\n|------|-------------|--------|\n| `get_person_profile` | 获取个人资料信息，并可选择特定部分（工作经历、教育背景、兴趣爱好、荣誉奖项、语言能力、证书资质、联系方式、动态） | 正常工作 |\n| `connect_with_person` | 发送好友请求或接受好友请求，可附带留言 | [#304](https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fissues\u002F304) |\n| `get_sidebar_profiles` | 从个人主页侧边栏推荐区域（“更多适合你的资料”、“探索高级资料”、“你可能认识的人”）提取资料链接 | 正常工作 |\n| `get_inbox` | 列出 LinkedIn 消息收件箱中的最近对话 | 正常工作 |\n| `get_conversation` | 根据用户名或线程 ID 阅读特定消息对话 | [#307](https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fissues\u002F307) |\n| `search_conversations` | 根据关键词搜索消息 | 正常工作 |\n| `send_message` | 向 LinkedIn 用户发送消息（需确认） | 正常工作 |\n| `get_company_profile` | 提取公司信息，并可选择特定部分（动态、职位） | 正常工作 |\n| `get_company_posts` | 获取公司 LinkedIn 主页上的最新动态 | 正常工作 |\n| `search_jobs` | 根据关键词和地点筛选搜索职位 | 正常工作 |\n| `search_people` | 根据关键词和地点搜索人员 | 正常工作 |\n| `get_job_details` | 获取特定职位的详细信息 | 正常工作 |\n| `close_session` | 关闭浏览器会话并清理资源 | 正常工作 |\n\n> [!重要提示]\n> **重大变更：** LinkedIn 近期进行了一些调整以防止数据抓取。最新版本使用了 [Patchright](https:\u002F\u002Fgithub.com\u002FKaliiiiiiiiii-Vinyzu\u002Fpatchright-python)，配合持久化的浏览器配置文件，取代了原先基于 Playwright 和会话文件的方式。旧的 `session.json` 文件以及 `LINKEDIN_COOKIE` 环境变量已不再支持。请重新运行 `--login` 命令以创建新的配置文件和 Cookie 文件，以便在 Docker 中挂载使用。2026年2月\n\n\u003Cbr\u002F>\n\u003Cbr\u002F>\n\n## 🚀 uvx 安装（推荐——通用）\n\n**先决条件：** [安装 uv](https:\u002F\u002Fdocs.astral.sh\u002Fuv\u002Fgetting-started\u002Finstallation\u002F)。\n\n### 安装\n\n**客户端配置**\n\n```json\n{\n  \"mcpServers\": {\n    \"linkedin\": {\n      \"command\": \"uvx\",\n      \"args\": [\"linkedin-scraper-mcp@latest\"],\n      \"env\": { \"UV_HTTP_TIMEOUT\": \"300\" }\n    }\n  }\n}\n```\n\n`@latest` 标签确保您始终运行最新版本——`uvx` 会在每次客户端启动时检查 PyPI 并自动更新。服务器会快速启动，在后台于 `~\u002F.linkedin-mcp\u002Fpatchright-browsers` 目录下准备共享的 Patchright Chromium 浏览器缓存，并在首次需要身份验证的工具调用时打开一个 LinkedIn 登录窗口。\n\n> [!注释]\n> 在浏览器设置或登录完成之前，早期的工具调用可能会返回“正在设置\u002F认证中”的错误。如果您希望显式创建会话，请运行 `uvx linkedin-scraper-mcp@latest --login`。\n\n### uvx 设置帮助\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>🔧 配置\u003C\u002Fb>\u003C\u002Fsummary>\n\n**传输模式：**\n\n- **默认 (stdio)**：本地 MCP 服务器的标准通信方式\n- **可流式 HTTP**：用于基于 Web 的 MCP 服务器\n- 如果未指定传输方式，服务器将默认使用 `stdio`\n- 在没有明确指定传输方式的情况下，交互式终端会显示一个选择提示\n\n**CLI 选项：**\n\n- `--login` - 打开浏览器登录并保存持久化配置文件\n- `--no-headless` - 显示浏览器窗口（有助于调试抓取问题）\n- `--log-level {DEBUG,INFO,WARNING,ERROR}` - 设置日志级别（默认：WARNING）\n- `--transport {stdio,streamable-http}` - 可选：强制指定传输模式（默认：stdio）\n- `--host HOST` - HTTP 服务器主机（默认：127.0.0.1）\n- `--port PORT` - HTTP 服务器端口（默认：8000）\n- `--path PATH` - HTTP 服务器路径（默认：\u002Fmcp）\n- `--logout` - 清除存储的 LinkedIn 浏览器配置文件\n- `--timeout MS` - 页面操作的浏览器超时时间，单位为毫秒（默认：5000）\n- `--user-data-dir PATH` - 持久化浏览器配置文件目录路径（默认：~\u002F.linkedin-mcp\u002Fprofile）\n- `--chrome-path PATH` - Chrome\u002FChromium 可执行文件路径（用于自定义浏览器安装）\n\n**基本使用示例：**\n\n```bash\n# 使用调试日志运行\nuvx linkedin-scraper-mcp@latest --log-level DEBUG\n```\n\n**HTTP 模式示例（适用于基于 Web 的 MCP 客户端）：**\n\n```bash\nuvx linkedin-scraper-mcp@latest --transport streamable-http --host 127.0.0.1 --port 8080 --path \u002Fmcp\n```\n\n运行时的服务器日志由 FastMCP\u002FUvicorn 输出。\n\n工具调用会在单个服务器进程中序列化，以保护共享的 LinkedIn 浏览器会话。并发客户端请求会被排队，而不是并行执行。使用 `--log-level DEBUG` 可查看抓取锁的等待\u002F获取\u002F释放日志。\n\n**使用 mcp 检查器测试：**\n\n1. 安装并运行 mcp 检查器 ```bunx @modelcontextprotocol\u002Finspector```\n2. 点击预填好的令牌 URL，在浏览器中打开检查器\n3. 将“传输类型”选择为“可流式 HTTP”\n4. 将“URL”设置为“http:\u002F\u002Flocalhost:8080\u002Fmcp”\n5. 连接\n6. 测试工具\n\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>❗ 故障排除\u003C\u002Fb>\u003C\u002Fsummary>\n\n**安装问题：**\n\n- 确保已安装 uv：`curl -LsSf https:\u002F\u002Fastral.sh\u002Fuv\u002Finstall.sh | sh`\n- 检查 uv 版本：`uv --version`（应为 0.4.0 或更高）\n- 首次运行时，`uvx` 会下载所有 Python 依赖项。在网速较慢的情况下，uv 默认的 30 秒 HTTP 超时可能过短。上述推荐配置已将 `UV_HTTP_TIMEOUT=300`（秒）设置，以避免此问题。\n\n**会话问题：**\n\n- 浏览器配置文件存储在 `~\u002F.linkedin-mcp\u002Fprofile\u002F`\n- 管理的浏览器下载缓存存储在 `~\u002F.linkedin-mcp\u002Fpatchright-browsers\u002F`\n- 确保一次只保持一个活跃的 LinkedIn 会话\n\n**登录问题：**\n\n- LinkedIn 可能需要在 LinkedIn 移动应用中进行登录确认才能完成 `--login`\n- 如果您频繁登录，可能会遇到验证码挑战。运行 `uvx linkedin-scraper-mcp@latest --login` 会打开一个浏览器窗口，您可以在其中手动解决验证码。\n\n**超时问题：**\n\n- 如果页面无法加载或找不到元素，请尝试增加超时时间：`--timeout 10000`\n- 网速较慢的用户可能需要更高的值（例如 15000–30000 毫秒）\n- 也可以通过环境变量设置：`TIMEOUT=10000`\n\n**自定义 Chrome 路径：**\n\n- 如果 Chrome 安装在非标准位置，可以使用 `--chrome-path \u002Fpath\u002Fto\u002Fchrome`\n- 也可以通过环境变量设置：`CHROME_PATH=\u002Fpath\u002Fto\u002Fchrome`\n\n\u003C\u002Fdetails>\n\n\u003Cbr\u002F>\n\u003Cbr\u002F>\n\n## 📦 Claude Desktop MCP 套件（原 DXT）\n\n**先决条件：** [Claude Desktop](https:\u002F\u002Fclaude.ai\u002Fdownload)。\n\n**Claude Desktop 用户的一键安装：**\n\n1. 从 [releases](https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Freleases\u002Flatest) 下载最新的 `.mcpb` 工件\n2. 点击下载的 `.mcpb` 文件将其安装到 Claude Desktop 中\n3. 调用任何 LinkedIn 工具\n\n启动时，MCP 套件会在后台开始准备共享的 Patchright Chromium 浏览器缓存。如果您过早调用工具，Claude 会显示正在设置中的错误。在首次需要身份验证的工具调用时，服务器会打开一个 LinkedIn 登录浏览器窗口，并提示您在登录后重试。\n\n### MCP 套件设置帮助\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>❗ 故障排除\u003C\u002Fb>\u003C\u002Fsummary>\n\n**首次设置行为：**\n\n- Claude Desktop 会立即启动套件；浏览器设置将在后台继续进行\n- 如果 Patchright Chromium 浏览器仍在下载中，请稍后再试工具\n- 管理的浏览器下载共享存储在 `~\u002F.linkedin-mcp\u002Fpatchright-browsers\u002F`\n\n**登录问题：**\n\n- 确保一次只保持一个活跃的 LinkedIn 会话\n- LinkedIn 可能需要在 LinkedIn 移动应用中进行登录确认才能完成 `--login`\n- 如果您频繁登录，可能会遇到验证码挑战。运行 `uvx linkedin-scraper-mcp@latest --login` 会打开一个浏览器窗口，您可以在其中手动解决验证码。请参阅 [uvx 设置](#-uvx-setup-recommended---universal) 了解先决条件。\n\n**超时问题：**\n\n- 如果页面无法加载或找不到元素，请尝试增加超时时间：`--timeout 10000`\n- 网速较慢的用户可能需要更高的值（例如 15000–30000 毫秒）\n- 也可以通过环境变量设置：`TIMEOUT=10000`\n\n\u003C\u002Fdetails>\n\n\u003Cbr\u002F>\n\u003Cbr\u002F>\n\n## 🐳 Docker 设置\n\n**先决条件：** 确保已安装并运行 [Docker](https:\u002F\u002Fwww.docker.com\u002Fget-started\u002F)，以及在主机上安装了 [uv](https:\u002F\u002Fdocs.astral.sh\u002Fuv\u002Fgetting-started\u002Finstallation\u002F) 以便进行一次性 `--login` 步骤。\n\n### 身份验证\n\nDocker 是无头运行（没有浏览器窗口），因此您需要先在本地创建一个浏览器配置文件，并将其挂载到容器中。\n\n**步骤 1：在主机上创建配置文件（一次性设置）**\n\n```bash\nuvx linkedin-scraper-mcp@latest --login\n```\n\n这会打开一个浏览器窗口，您可以在其中手动登录（2FA、验证码等有 5 分钟超时）。浏览器配置文件和 Cookie 会保存在 `~\u002F.linkedin-mcp\u002F` 目录下。启动时，Docker 会从您的主机 Cookie 中派生出 Linux 浏览器配置文件，并每次创建一个新的会话。如果您在使用 Docker 时遇到稳定性问题，建议改用 [uvx 设置](#-uvx-setup-recommended---universal)。\n\n**步骤 2：使用 Docker 配置 Claude Desktop**\n\n```json\n{\n  \"mcpServers\": {\n    \"linkedin\": {\n      \"command\": \"docker\",\n      \"args\": [\n        \"run\", \"--rm\", \"-i\",\n        \"-v\", \"~\u002F.linkedin-mcp:\u002Fhome\u002Fpwuser\u002F.linkedin-mcp\",\n        \"stickerdaniel\u002Flinkedin-mcp-server:latest\"\n      ]\n    }\n  }\n}\n```\n\n> [!NOTE]\n> Docker 每次启动都会创建一个新的会话。会话可能会随着时间推移而失效——如果遇到身份验证问题，请再次运行 `uvx linkedin-scraper-mcp@latest --login`。\n\n> [!NOTE]\n> **为什么不能在 Docker 中运行 `--login`？** Docker 容器没有显示服务器。请使用 [uvx 设置](#-uvx-setup-recommended---universal) 在您的主机上创建配置文件，并将其挂载到 Docker 中。\n\n### Docker 设置帮助\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>🔧 配置\u003C\u002Fb>\u003C\u002Fsummary>\n\n**传输模式：**\n\n- **默认 (stdio)**：用于本地 MCP 服务器的标准通信\n- **可流式 HTTP**：适用于基于 Web 的 MCP 服务器\n- 如果未指定传输方式，服务器将默认使用 `stdio`\n- 在没有明确指定传输方式的情况下，交互式终端会显示一个选择提示\n\n**CLI 选项：**\n\n- `--log-level {DEBUG,INFO,WARNING,ERROR}` - 设置日志级别（默认：WARNING）\n- `--transport {stdio,streamable-http}` - 可选：强制指定传输模式（默认：stdio）\n- `--host HOST` - HTTP 服务器主机（默认：127.0.0.1）\n- `--port PORT` - HTTP 服务器端口（默认：8000）\n- `--path PATH` - HTTP 服务器路径（默认：\u002Fmcp）\n- `--logout` - 清除所有存储的 LinkedIn 身份验证状态，包括源和派生的运行时配置文件\n- `--timeout MS` - 浏览器页面操作的超时时间，单位为毫秒（默认：5000）\n- `--user-data-dir PATH` - 持久化浏览器配置文件目录的路径（默认：~\u002F.linkedin-mcp\u002Fprofile）\n- `--chrome-path PATH` - Chrome\u002FChromium 可执行文件的路径（在 Docker 中很少需要）\n\n> [!NOTE]\n> `--login` 和 `--no-headless` 在 Docker 中不可用（因为没有显示服务器）。请使用 [uvx 设置](#-uvx-setup-recommended---universal) 来创建配置文件。\n\n**HTTP 模式示例（适用于基于 Web 的 MCP 客户端）：**\n\n```bash\ndocker run -it --rm \\\n  -v ~\u002F.linkedin-mcp:\u002Fhome\u002Fpwuser\u002F.linkedin-mcp \\\n  -p 8080:8080 \\\n  stickerdaniel\u002Flinkedin-mcp-server:latest \\\n  --transport streamable-http --host 0.0.0.0 --port 8080 --path \u002Fmcp\n```\n\n运行时服务器日志由 FastMCP\u002FUvicorn 输出。\n\n**使用 mcp 检查器进行测试：**\n\n1. 安装并运行 mcp 检查器 ```bunx @modelcontextprotocol\u002Finspector```\n2. 点击预填充的令牌 URL，在浏览器中打开检查器\n3. 将“传输类型”设置为“可流式 HTTP”\n4. 将“URL”设置为“http:\u002F\u002Flocalhost:8080\u002Fmcp”\n5. 连接\n6. 测试工具\n\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>❗ 故障排除\u003C\u002Fb>\u003C\u002Fsummary>\n\n**Docker 问题：**\n\n- 确保已安装 [Docker](https:\u002F\u002Fwww.docker.com\u002Fget-started\u002F)\n- 检查 Docker 是否正在运行：`docker ps`\n\n**登录问题：**\n\n- 确保一次只保持一个活动的 LinkedIn 会话\n- 使用 `--login` 时，LinkedIn 可能会在手机应用中要求登录确认\n- 如果您频繁登录，可能会遇到验证码挑战。此时可以运行 `uvx linkedin-scraper-mcp@latest --login`，这将打开一个浏览器窗口，您可以在其中手动解决验证码。有关先决条件，请参阅 [uvx 设置](#-uvx-setup-recommended---universal)。\n- 如果在主机上重新登录后，Docker 的身份验证信息过期，请重启一次 Docker，以便它能够从新的源会话中重新建立连接。\n\n**超时问题：**\n\n- 如果页面无法加载或找不到元素，可以尝试增加超时时间：`--timeout 10000`\n- 对于网络较慢的用户，可能需要更高的值（例如 15000-30000 毫秒）\n- 也可以通过环境变量设置：`TIMEOUT=10000`\n\n**自定义 Chrome 路径：**\n\n- 如果 Chrome 安装在非标准位置，可以使用 `--chrome-path \u002Fpath\u002Fto\u002Fchrome`\n- 也可以通过环境变量设置：`CHROME_PATH=\u002Fpath\u002Fto\u002Fchrome`\n\n\u003C\u002Fdetails>\n\n\u003Cbr\u002F>\n\u003Cbr\u002F>\n\n## 🐍 本地设置（开发与贡献）\n\n欢迎贡献！请参阅 [CONTRIBUTING.md](CONTRIBUTING.md) 以获取架构指南和检查清单。在提交 PR 之前，请先[打开一个问题](https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fissues)，讨论功能或错误修复。\n\n**先决条件：** 已安装 [Git](https:\u002F\u002Fgit-scm.com\u002Fdownloads) 和 [uv](https:\u002F\u002Fdocs.astral.sh\u002Fuv\u002F)\n\n### 安装\n\n```bash\n# 1. 克隆仓库\ngit clone https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\ncd linkedin-mcp-server\n\n# 2. 安装 UV 包管理器（如果尚未安装）\ncurl -LsSf https:\u002F\u002Fastral.sh\u002Fuv\u002Finstall.sh | sh\n\n# 3. 安装依赖项\nuv sync\nuv sync --group dev\n\n# 4. 安装 pre-commit 钩子\nuv run pre-commit install\n\n# 5. 启动服务器\nuv run -m linkedin_mcp_server\n```\n\n本地服务器使用与 MCPB 和 `uvx` 相同的托管运行时流程：它会在后台准备 Patchright Chromium 浏览器缓存，并在首次调用需要身份验证的工具时打开 LinkedIn 登录界面。如果您想显式创建会话，仍然可以运行 `uv run -m linkedin_mcp_server --login`。\n\n### 本地设置帮助\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>🔧 配置\u003C\u002Fb>\u003C\u002Fsummary>\n\n**命令行选项：**\n\n- `--login` - 打开浏览器进行登录并保存持久化配置文件\n- `--no-headless` - 显示浏览器窗口（有助于调试抓取问题）\n- `--log-level {DEBUG,INFO,WARNING,ERROR}` - 设置日志级别（默认：WARNING）\n- `--transport {stdio,streamable-http}` - 可选：强制传输模式（默认：stdio）\n- `--host HOST` - HTTP服务器主机（默认：127.0.0.1）\n- `--port PORT` - HTTP服务器端口（默认：8000）\n- `--path PATH` - HTTP服务器路径（默认：\u002Fmcp）\n- `--logout` - 清除存储的LinkedIn浏览器配置文件\n- `--timeout MS` - 浏览器页面操作超时时间，单位为毫秒（默认：5000）\n- `--status` - 检查当前会话是否有效并退出\n- `--user-data-dir PATH` - 持久化浏览器配置文件目录路径（默认：~\u002F.linkedin-mcp\u002Fprofile）\n- `--slow-mo MS` - 浏览器操作之间的延迟时间，单位为毫秒（默认：0，可用于调试）\n- `--user-agent STRING` - 自定义浏览器用户代理\n- `--viewport WxH` - 浏览器视口大小（默认：1280x720）\n- `--chrome-path PATH` - Chrome\u002FChromium可执行文件路径（用于自定义浏览器安装）\n- `--help` - 显示帮助信息\n\n> **注意：** 大多数命令行选项都有对应的环境变量。详情请参阅 `.env.example`。\n\n**HTTP模式示例（适用于基于Web的MCP客户端）：**\n\n```bash\nuv run -m linkedin_mcp_server --transport streamable-http --host 127.0.0.1 --port 8000 --path \u002Fmcp\n```\n\n**Claude Desktop：**\n\n```json\n{\n  \"mcpServers\": {\n    \"linkedin\": {\n      \"command\": \"uv\",\n      \"args\": [\"--directory\", \"\u002Fpath\u002Fto\u002Flinkedin-mcp-server\", \"run\", \"-m\", \"linkedin_mcp_server\"]\n    }\n  }\n}\n```\n\n此配置默认使用 `stdio` 模式。\n\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>❗ 故障排除\u003C\u002Fb>\u003C\u002Fsummary>\n\n**登录问题：**\n\n- 确保一次只保持一个活跃的LinkedIn会话\n- 使用 `--login` 时，LinkedIn可能需要在手机App中进行登录确认\n- 如果频繁登录，可能会触发验证码挑战。`--login` 命令会打开浏览器，您可以在其中手动解决验证码。\n\n**抓取问题：**\n\n- 使用 `--no-headless` 查看浏览器操作过程，以便调试抓取问题\n- 添加 `--log-level DEBUG` 以获取更详细的日志信息\n\n**会话问题：**\n\n- 浏览器配置文件存储在 `~\u002F.linkedin-mcp\u002Fprofile\u002F`\n- 使用 `--logout` 清除配置文件并重新开始\n\n**Python\u002FPatchright问题：**\n\n- 检查Python版本：`python --version`（应为3.12及以上）\n- 重新安装Patchright：`uv run patchright install chromium`\n- 重新安装依赖项：`uv sync --reinstall`\n\n**超时问题：**\n\n- 如果页面无法加载或找不到元素，尝试增加超时时间：`--timeout 10000`\n- 对于网络较慢的用户，可能需要更高的值（例如15000-30000毫秒）\n- 也可以通过环境变量设置：`TIMEOUT=10000`\n\n**自定义Chrome路径：**\n\n- 如果Chrome安装在非标准位置，使用 `--chrome-path \u002Fpath\u002Fto\u002Fchrome`\n- 也可以通过环境变量设置：`CHROME_PATH=\u002Fpath\u002Fto\u002Fchrome`\n\n\u003C\u002Fdetails>\n\n\n\u003Cbr\u002F>\n\u003Cbr\u002F>\n\n## 致谢\n\n基于 [FastMCP](https:\u002F\u002Fgofastmcp.com\u002F) 和 [Patchright](https:\u002F\u002Fgithub.com\u002FKaliiiiiiiiii-Vinyzu\u002Fpatchright-python) 构建。\n\n请遵守 [LinkedIn服务条款](https:\u002F\u002Fwww.linkedin.com\u002Flegal\u002Fuser-agreement) 使用本工具。网络爬虫行为可能违反LinkedIn的服务条款。本工具仅供个人使用。\n\n## 许可证\n\n本项目采用Apache 2.0许可证。","# LinkedIn MCP Server 快速上手指南\n\nLinkedIn MCP Server 是一个允许 AI 助手（如 Claude）连接你的 LinkedIn 账户的工具。通过它，你可以查询个人\u002F公司档案、搜索职位、获取职位详情以及进行消息交互。\n\n## 环境准备\n\n在开始之前，请确保满足以下系统要求：\n\n*   **操作系统**：Linux, macOS 或 Windows (WSL 推荐)\n*   **核心依赖**：必须安装 [uv](https:\u002F\u002Fdocs.astral.sh\u002Fuv\u002Fgetting-started\u002Finstallation\u002F) (Python 包管理工具)。\n    *   安装命令 (Linux\u002FmacOS):\n        ```bash\n        curl -LsSf https:\u002F\u002Fastral.sh\u002Fuv\u002Finstall.sh | sh\n        ```\n    *   验证安装：\n        ```bash\n        uv --version\n        ```\n*   **网络环境**：由于需要访问 LinkedIn，请确保网络通畅。如果下载浏览器内核缓慢，可能需要配置全局代理。\n*   **客户端**：已安装支持 MCP 协议的 AI 客户端（如 Claude Desktop）。\n\n> **重要提示**：最新版本使用 [Patchright](https:\u002F\u002Fgithub.com\u002FKaliiiiiiiiii-Vinyzu\u002Fpatchright-python) 持久化浏览器配置文件。旧的 `session.json` 文件或 `LINKEDIN_COOKIE` 环境变量已不再支持。首次使用前必须执行登录步骤以生成新的配置文件。\n\n## 安装步骤\n\n推荐使用 **uvx** 方式进行安装，它会自动处理依赖并始终运行最新版本。\n\n### 1. 配置 MCP 客户端\n\n在你的 MCP 客户端配置文件（例如 Claude Desktop 的 `claude_desktop_config.json`）中添加以下配置：\n\n```json\n{\n  \"mcpServers\": {\n    \"linkedin\": {\n      \"command\": \"uvx\",\n      \"args\": [\"linkedin-scraper-mcp@latest\"],\n      \"env\": { \"UV_HTTP_TIMEOUT\": \"300\" }\n    }\n  }\n}\n```\n\n*   `@latest` 标签确保每次启动时自动检查并更新到 PyPI 上的最新版本。\n*   `UV_HTTP_TIMEOUT=300` 用于防止在网络较慢时下载依赖超时。\n\n### 2. 执行登录认证 (必需)\n\n配置完成后，服务器会在首次需要认证的调用时自动弹出浏览器窗口。你也可以手动预先完成登录以创建持久化配置文件：\n\n```bash\nuvx linkedin-scraper-mcp@latest --login\n```\n\n*   执行该命令后，会打开一个浏览器窗口。\n*   请在窗口中完成 LinkedIn 登录（包括可能的手机验证码或滑块验证）。\n*   登录成功后，浏览器配置文件将保存在 `~\u002F.linkedin-mcp\u002Fprofile\u002F` 目录下。\n*   **注意**：请确保同一时间只有一个活跃的 LinkedIn 会话，避免冲突。\n\n## 基本使用\n\n配置并登录成功后，你可以在支持的 AI 助手（如 Claude）中直接使用自然语言调用 LinkedIn 功能。\n\n**使用示例：**\n\n1.  **调研候选人背景**\n    ```text\n    Research the background of this candidate https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fstickerdaniel\u002F\n    ```\n\n2.  **获取公司档案以进行合作讨论**\n    ```text\n    Get this company profile for partnership discussions https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002Finframs\u002F\n    ```\n\n3.  **针对特定职位优化简历**\n    ```text\n    Suggest improvements for my CV to target this job posting https:\u002F\u002Fwww.linkedin.com\u002Fjobs\u002Fview\u002F4252026496\n    ```\n\n4.  **查询公司近期动态**\n    ```text\n    What has Anthropic been posting about recently? https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002Fanthropicresearch\u002F\n    ```\n\n**可用功能概览：**\n*   `get_person_profile`: 获取个人资料（经历、教育、技能等）。\n*   `get_company_profile`: 获取公司信息及动态。\n*   `search_jobs` \u002F `get_job_details`: 搜索职位及查看详情。\n*   `search_people`: 搜索用户。\n*   `get_inbox` \u002F `send_message`: 查看收件箱及发送消息（需确认）。","某科技公司的招聘经理正急需为一个新的 AI 项目组建团队，需要在短时间内从海量候选人中筛选出具备特定大模型微调经验的资深工程师，并发起初步接触。\n\n### 没有 linkedin-mcp-server 时\n- **信息获取割裂**：必须在浏览器中手动打开数十个候选人主页，逐页复制粘贴经历到文档中，效率极低且容易出错。\n- **上下文切换频繁**：在查看职位详情、比对候选人技能树和撰写面试邀请之间反复跳转，注意力被严重分散。\n- **个性化沟通困难**：难以快速回顾与候选人的历史聊天记录或根据其最新动态定制问候语，导致发出的邀请显得模板化，回复率低。\n- **数据整合滞后**：无法实时将候选人的最新认证或项目经历同步到内部评估表中，决策依据往往滞后于实际情况。\n\n### 使用 linkedin-mcp-server 后\n- **一键深度洞察**：直接在 Claude 对话框中输入链接，工具自动提取并总结候选人的核心技能、项目经验及认证信息，瞬间生成结构化报告。\n- **智能人岗匹配**：让 AI 对比职位描述与候选人档案，自动高亮匹配度最高的三位人选并给出推荐理由，无需人工逐条比对。\n- **定制化即时触达**：基于提取的候选人最新动态（如刚发布的文章或新获荣誉），指挥工具草拟并发送高度个性化的连接请求或站内信。\n- **全流程闭环操作**：在同一个对话窗口内即可完成从“搜索职位”、“分析人才”到“发送消息”的全流程，无需离开终端界面。\n\nlinkedin-mcp-server 将原本需要数小时的手工调研与沟通工作压缩至分钟级，让招聘者能专注于战略决策而非繁琐的数据搬运。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fstickerdaniel_linkedin-mcp-server_c4944c91.png","stickerdaniel","Daniel Sticker ","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fstickerdaniel_1bf6af31.png","Computer Science @ RWTH Aachen",null,"Aachen, Germany","inframs.de","https:\u002F\u002Fgithub.com\u002Fstickerdaniel",[82,86],{"name":83,"color":84,"percentage":85},"Python","#3572A5",99.8,{"name":87,"color":88,"percentage":89},"Dockerfile","#384d54",0.2,1301,241,"2026-04-07T22:11:29","Apache-2.0","Linux, macOS, Windows","未说明",{"notes":97,"python":98,"dependencies":99},"1. 推荐使用 uv\u002Fuvx 进行安装和管理依赖。2. 核心依赖是 Patchright (基于 Playwright 的分支)，用于控制浏览器，不再支持旧的 session.json 或 LINKEDIN_COOKIE。3. 首次运行或登录时会下载并缓存 Chromium 浏览器到 ~\u002F.linkedin-mcp\u002Fpatchright-browsers。4. Docker 部署需先在宿主机通过 --login 创建浏览器配置文件。5. 需要保持单一活跃的 LinkedIn 会话以避免冲突。","由 uv\u002Fuvx 自动管理 (未指定具体版本)",[100,101,102],"patchright-python","fastmcp","uvicorn",[13,35,52],[105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123],"linkedin","linkedin-scraper","mcp","mcp-server","linkedin-mcp","claude-desktop","desktop-extension","dxt","linkedin-profile-scraper","anthropic","chatgpt","chatgpt-desktop","claude","model-context-protocol","ai-agents","claude-code","linkedin-api","python","claude-ai","2026-03-27T02:49:30.150509","2026-04-08T12:12:54.730024",[127,132,137,142,147,151],{"id":128,"question_zh":129,"answer_zh":130,"source_url":131},24263,"为什么即使使用了正确的 Cookie，仍然出现认证错误？","这通常是因为旧的基于 Cookie 的认证方式已不再稳定。请在 v2 版本中使用新的基于会话（session-based）的认证方式来解决此问题。运行命令 `--get-session` 来创建一个全新的会话文件，而不是手动复制粘贴 Cookie。","https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fissues\u002F40",{"id":133,"question_zh":134,"answer_zh":135,"source_url":136},24264,"遇到“速率限制（Rate limit detected）”错误该怎么办？","该错误通常是因为 LinkedIn 在后台加载了不可见的 reCAPTCHA 验证，从而触发了反爬虫机制。即使没有频繁请求也可能发生。目前的临时解决方法是等待约 30 秒后重试，或者清除认证信息并重新进行认证（re-auth），但如果是被标记为 CAPTCHA 挑战，可能需要人工介入或在非头模式（non-headless）下操作以通过验证。","https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fissues\u002F136",{"id":138,"question_zh":139,"answer_zh":140,"source_url":141},24265,"运行 `uvx ... --get-session` 登录后无法退出且未生成 session.json 文件怎么办？","这个问题通常发生在用户登录后被重定向到 `\u002Ffeed` 页面，而程序未能正确检测到登录完成状态。这是一个已知的上游抓取器问题。建议检查登录后是否停留在 `\u002Ffeed` 页面。如果问题持续，尝试在非头模式（visible browser）下运行以确保能观察到浏览器行为，或关注项目后续更新以修复对 `\u002Ffeed` 页面的检测逻辑。","https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fissues\u002F95",{"id":143,"question_zh":144,"answer_zh":145,"source_url":146},24266,"如何正确获取和配置 LinkedIn Cookie 以避免认证失败？","仅仅通过浏览器开发者工具获取 `li_at` Cookie 并在登出后使用往往会导致认证失败，因为 Cookie 可能已失效或与当前会话绑定。推荐的做法是升级到最新版本，使用 `--get-session` 参数让工具自动启动浏览器并完成登录流程，从而生成有效的 `session.json` 文件，避免手动处理 Cookie 的复杂性。","https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fissues\u002F31",{"id":148,"question_zh":149,"answer_zh":150,"source_url":131},24267,"在非头模式（non-headless）下手动登录是否有助于解决连接问题？","是的，许多用户在遇到自动登录失败或 Cookie 无效错误时发现，在非头模式（即显示浏览器界面）下运行服务器，允许手动完成登录过程（包括处理可能的 CAPTCHA），通常能成功建立会话并使工具正常工作。可以在配置中将 `headless` 设置为 `false` 来启用此模式。",{"id":152,"question_zh":153,"answer_zh":154,"source_url":155},24268,"为什么在 Docker 或本地安装后无法获取个人资料信息？","这通常是由于认证会话过期或无效导致的权限问题。请确保您使用的是最新的 v2 版本，并通过 `--get-session` 命令重新生成有效的会话文件。如果问题依旧，尝试在非头模式下运行以确认是否能手动通过 LinkedIn 的安全验证。","https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fissues\u002F42",[157,162,167,172,177,182,187,192,197,202,207,212,217,222,227,232,237,242,247,252],{"id":158,"version":159,"summary_zh":160,"released_at":161},147579,"v4.8.2","有关安装指南，请参阅 [README](https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fblob\u002Fmain\u002FREADME.md)。\n\n## 📦 更新 MCP 包安装\n**适用于 Claude Desktop 用户：**\n1. 下载下方的 `.mcpb` 文件。\n2. 点击该 `.mcpb` 文件以在 Claude Desktop 中进行安装。\n\n> **注意：** MCP 包（MCPB）是 DXT\u002F桌面扩展的更名后继版本。\n\n## 🐳 更新 Docker 安装\n**适用于使用基于 Docker 的 MCP 客户端配置的用户：**\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:latest\n```\n`latest` 标签始终指向最新版本。若要拉取此特定版本，请运行：\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:4.8.2\n```\n\n\n## 变更内容\n* 测试：移除本地会卡死的 Bootstrap 测试，由 @stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F309 中完成。\n* 文档（README）：同步工具状态与问题，由 @stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F322 中完成。\n* 文档（README）：将工具状态与未解决的问题同步，由 @stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F324 中完成。\n* 功能：爬虫优化——为 `get_person_profile` 添加证书部分，由 @stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F326 中完成。\n* 杂项：将版本号更新至 4.8.2，由 @stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F327 中完成。\n\n\n**完整变更日志**：https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fcommits\u002Fv4.8.2","2026-04-06T08:59:46",{"id":163,"version":164,"summary_zh":165,"released_at":166},147580,"v4.8.1","有关安装指南，请参阅[README](https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fblob\u002Fmain\u002FREADME.md)。\n\n## 📦 更新 MCP 包安装\n**适用于 Claude Desktop 用户：**\n1. 下载下方的 `.mcpb` 文件\n2. 点击 `.mcpb` 文件，在 Claude Desktop 中进行安装\n\n> **注意：** MCP 包（MCPB）是 DXT\u002F桌面扩展的更名后继版本。\n\n## 🐳 更新 Docker 安装\n**适用于使用基于 Docker 的 MCP 客户端配置的用户：**\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:latest\n```\n`latest` 标签始终指向最新版本。若要拉取此特定版本，运行：\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:4.8.1\n```\n\n\n## 变更内容\n* 修复（抓取）：在消息功能中尊重 `--timeout` 参数，由 @stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F300 中实现，用于提取收件箱线程 ID。\n* 杂项：由 @stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F301 中将版本号提升至 4.8.1。\n\n\n**完整变更日志**：https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fcompare\u002Fv4.8.0...v4.8.1","2026-03-31T10:35:37",{"id":168,"version":169,"summary_zh":170,"released_at":171},147581,"v4.8.0","有关安装指南，请参阅 [README](https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fblob\u002Fmain\u002FREADME.md)。\n\n## 📦 更新 MCP 包安装\n**适用于 Claude Desktop 用户：**\n1. 下载下方的 `.mcpb` 文件。\n2. 点击该 `.mcpb` 文件，即可在 Claude Desktop 中进行安装。\n\n> **注意：** MCP 包（MCPB）是 DXT\u002F桌面扩展的更名后继版本。\n\n## 🐳 更新 Docker 安装\n**适用于使用基于 Docker 的 MCP 客户端配置的用户：**\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:latest\n```\n`latest` 标签始终指向最新版本。若要拉取特定版本，请运行：\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:4.8.0\n```\n\n\n## 变更内容\n* chore(deps): 更新 CI 依赖项，由 @renovate[bot] 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F292 中完成。\n* 加强 .linkedin-mcp 配置文件\u002FCookie 权限，由 @shuofengzhang 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F283 中完成。\n* feat: LinkedIn 消息功能，获取侧边栏个人资料，由 @aspectrr 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F291 中实现。\n* chore: 将版本号提升至 4.8.0，由 @stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F294 中完成。\n\n\n**完整变更日志**：https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fcompare\u002Fv4.7.2...v4.8.0","2026-03-30T16:52:59",{"id":173,"version":174,"summary_zh":175,"released_at":176},147582,"v4.7.2","有关安装指南，请参阅[README](https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fblob\u002Fmain\u002FREADME.md)。\n\n## 📦 更新 MCP 包安装\n**适用于 Claude Desktop 用户：**\n1. 下载下方的 `.mcpb` 文件\n2. 点击该 `.mcpb` 文件，在 Claude Desktop 中进行安装\n\n> **注意：** MCP 包（MCPB）是 DXT\u002F桌面扩展的更名后继版本。\n\n## 🐳 更新 Docker 安装\n**适用于使用基于 Docker 的 MCP 客户端配置的用户：**\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:latest\n```\n`latest` 标签始终指向最新版本。若要拉取特定版本，可运行：\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:4.7.2\n```\n\n\n## 变更内容\n* 功能（connect）：添加“更多”菜单支持，并返回个人资料文本，由 @stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F289 中实现。\n* 杂项：将版本号升级至 4.7.2，由 @stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F290 中完成。\n\n\n**完整变更日志**：https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fcompare\u002Fv4.7.1...v4.7.2","2026-03-29T09:43:34",{"id":178,"version":179,"summary_zh":180,"released_at":181},147583,"v4.7.1","有关安装指南，请参阅 [README](https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fblob\u002Fmain\u002FREADME.md)。\n\n## 📦 更新 MCP 包安装\n**适用于 Claude Desktop 用户：**\n1. 下载下方的 `.mcpb` 文件。\n2. 点击该 `.mcpb` 文件，即可在 Claude Desktop 中进行安装。\n\n> **注意：** MCP 包（MCPB）是 DXT\u002F桌面扩展的更名后继版本。\n\n## 🐳 更新 Docker 安装\n**适用于使用基于 Docker 的 MCP 客户端配置的用户：**\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:latest\n```\n`latest` 标签始终指向最新版本。若要拉取特定版本，可运行以下命令：\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:4.7.1\n```\n\n\n## 变更内容\n* docs：@stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F286 中更新了 `connect_with_person` 的描述。\n* fix(connect)：@stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F287 中实现了精确文本匹配，并在点击前滚动到页面顶部。\n* chore：@stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F288 中将版本号升级至 4.7.1。\n\n\n**完整变更日志**：https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fcompare\u002Fv4.7.0...v4.7.1","2026-03-29T09:14:40",{"id":183,"version":184,"summary_zh":185,"released_at":186},147584,"v4.7.0","有关安装指南，请参阅 [README](https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fblob\u002Fmain\u002FREADME.md)。\n\n## 📦 更新 MCP 包安装\n**适用于 Claude Desktop 用户：**\n1. 下载下方的 `.mcpb` 文件。\n2. 点击该 `.mcpb` 文件以在 Claude Desktop 中进行安装。\n\n> **注意：** MCP 包（MCPB）是 DXT\u002F桌面扩展的更名后继版本。\n\n## 🐳 更新 Docker 安装\n**适用于使用基于 Docker 的 MCP 客户端配置的用户：**\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:latest\n```\n`latest` 标签始终指向最新版本。若要拉取此特定版本，请运行：\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:4.7.0\n```\n\n\n## 变更内容\n* 修复（安全）：固定 CI 依赖项，强化文件权限，并在使用 `0.0.0.0` 时发出警告，由 @stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F272 中完成。\n* 重构（common_utils）：使用 `mkstemp` 进行安全文本写入，由 @stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F273 中完成。\n* 功能改进（进度）：将章节级进度集成到 `scrape_person` 和 `scrape_company` 中，由 @stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F275 中完成。\n* 功能改进（技能）：添加用于 PR 审核验证的 `triaje-reviews` 技能，由 @stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F276 中完成。\n* 功能改进（认证）：在会话过期时自动重新登录，而非手动执行 `--login` 操作，由 @stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F277 中完成。\n* 修复（技能）：为 `triaje-reviews` 添加分页功能及错误处理机制，由 @stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F281 中完成。\n* 修复（安全）：对 `~\u002F.linkedin-mcp` 目录下的所有子目录使用 `secure_mkdir`，由 @stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F280 中完成。\n* 修复（安全）：在 `secure_mkdir` 中为所有父目录应用权限模式，由 @stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F282 中完成。\n* 杂项：更新 BTCA 文档并添加 `patchright` 资源，由 @stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F284 中完成。\n* 功能改进：增加通过 MCP 连接的功能，由 @aspectrr 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F274 中完成。\n* 杂项：将版本号提升至 4.7.0，由 @stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F285 中完成。\n\n## 新贡献者\n* @aspectrr 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F274 中完成了首次贡献。\n\n**完整变更日志**：https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fcompare\u002Fv4.6.1...v4.7.0","2026-03-29T00:27:53",{"id":188,"version":189,"summary_zh":190,"released_at":191},147585,"v4.6.1","有关安装指南，请参阅 [README](https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fblob\u002Fmain\u002FREADME.md)。\n\n## 📦 更新 MCP 包安装\n**适用于 Claude Desktop 用户：**\n1. 下载下方的 `.mcpb` 文件。\n2. 点击该 `.mcpb` 文件，即可在 Claude Desktop 中进行安装。\n\n> **注意：** MCP 包（MCPB）是 DXT\u002F桌面扩展的更名后继版本。\n\n## 🐳 更新 Docker 安装\n**适用于使用基于 Docker 的 MCP 客户端配置的用户：**\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:latest\n```\n`latest` 标签始终指向最新版本。若要拉取此特定版本，请运行：\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:4.6.1\n```\n\n\n## 变更内容\n* 文档：修复发布说明模板中的安装步骤表述，由 @stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F264 中完成。\n* 文档：修复 README 中的安装步骤表述，由 @stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F265 中完成。\n* 规范化配置加载时的环境变量解析，由 @shuofengzhang 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F209 中完成。\n* 确保在执行登录时验证浏览器是否已安装，由 @perfectra1n 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F269 中完成。\n* 杂项：将版本号提升至 4.6.1，由 @stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F270 中完成。\n\n## 新贡献者\n* @shuofengzhang 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F209 中完成了首次贡献。\n* @perfectra1n 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F269 中完成了首次贡献。\n\n**完整变更日志**：https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fcompare\u002Fv4.6.0...v4.6.1","2026-03-25T01:33:34",{"id":193,"version":194,"summary_zh":195,"released_at":196},147586,"v4.6.0","有关安装指南，请参阅[README](https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fblob\u002Fmain\u002FREADME.md)。\n\n## 📦 更新 MCP 套件安装\n**适用于 Claude Desktop 用户：**\n1. 下载下方的 `.mcpb` 文件。\n2. 双击 `.mcpb` 文件，即可在 Claude Desktop 中进行安装。\n\n> **注意：** MCP 套件（MCPB）是 DXT\u002F桌面扩展的更名后继版本。\n\n## 🐳 更新 Docker 安装\n**适用于使用基于 Docker 的 MCP 客户端配置的用户：**\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:latest\n```\n`latest` 标签始终指向最新版本。若要拉取此特定版本，请运行：\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:4.6.0\n```\n\n\n## 更改内容\n* 修复（登录）：在登录过程中将 `--chrome-path` 参数传递给 BrowserManager，由 @NickDriver 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F261 中完成。\n* 修复（登录）：在登录过程中转发所有浏览器配置参数，由 @stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F262 中完成。\n* 杂项：将版本号升级至 4.6.0，由 @stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F263 中完成。\n\n## 新贡献者\n* @NickDriver 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F261 中完成了首次贡献。\n\n**完整变更日志**：https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fcompare\u002Fv4.5.3...v4.6.0","2026-03-22T18:09:30",{"id":198,"version":199,"summary_zh":200,"released_at":201},147587,"v4.5.3","有关安装指南，请参阅 [README](https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fblob\u002Fmain\u002FREADME.md)。\n\n## 📦 更新 MCP Bundle 安装\n**适用于 Claude Desktop 用户：**\n1. 下载下方的 `.mcpb` 文件。\n2. 双击 `.mcpb` 文件，即可在 Claude Desktop 中进行安装。\n\n> **注意：** MCP Bundles（MCPB）是 DXT\u002FDesktop Extensions 的新名称版本。\n\n## 🐳 更新 Docker 安装\n**适用于使用基于 Docker 的 MCP 客户端配置的用户：**\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:latest\n```\n`latest` 标签始终指向最新版本。若要拉取特定版本，请运行：\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:4.5.3\n```\n\n\n## 更改内容\n* docs(mcpb)：由 @stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F256 中简化了安装步骤。\n* fix(docker)：由 @stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F258 中使用 Python 3.13 基础镜像修复权限拒绝错误。\n* chore：由 @stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F259 中将版本号更新至 4.5.3。\n\n\n**完整变更日志**：https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fcompare\u002Fv4.5.2...v4.5.3","2026-03-22T17:29:17",{"id":203,"version":204,"summary_zh":205,"released_at":206},147588,"v4.5.2","有关安装指南，请参阅 [README](https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fblob\u002Fmain\u002FREADME.md)。\n\n## 🐳 更新 Docker 安装\n**适用于使用 Docker 部署 MCP 客户端的用户：**\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:latest\n```\n`latest` 标签始终指向最新版本。若要拉取此特定版本，请运行：\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:4.5.2\n```\n\n## 📦 更新 MCP Bundle 安装\n**适用于 Claude Desktop 用户：**\n1. 下载下方的 `.mcpb` 文件。\n2. 双击 `.mcpb` 文件以在 Claude Desktop 中安装。\n3. 重启 Claude Desktop。\n\n> **注意：** MCP Bundles（MCPB）是 DXT\u002FDesktop Extensions 的新名称版本。\n\n## 更改内容\n* docs：由 @stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F254 中精简了 README 安装文档。\n* fix(mcpb)：由 @stickerdaniel 在 https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F255 中固定了支持的 Python 版本。\n\n\n**完整变更日志**：https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fcompare\u002Fv4.5.1...v4.5.2","2026-03-21T18:26:56",{"id":208,"version":209,"summary_zh":210,"released_at":211},147589,"v4.5.1","For an installation guide, refer to the [README](https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fblob\u002Fmain\u002FREADME.md).\n\n## 🐳 Update Docker Installation\n**For users with Docker-based MCP client configurations:**\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:latest\n```\nThe `latest` tag will always point to the most recent release.\nTo pull this specific version, run:\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:4.5.1\n```\n\n## 📦 Update MCP Bundle Installation\n**For Claude Desktop users:**\n1. Download the `.mcpb` file below\n2. Double-click the `.mcpb` file to install in Claude Desktop\n3. Restart Claude Desktop\n\n> **Note:** MCP Bundles (MCPB) are the renamed successor to DXT\u002FDesktop Extensions.\n\n\n## What's Changed\n* fix(ci): repair release workflow by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F253\n\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fcompare\u002Fv4.5.0...v4.5.1","2026-03-21T17:46:15",{"id":213,"version":214,"summary_zh":215,"released_at":216},147590,"v4.4.2","For an installation guide, refer to the [README](https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fblob\u002Fmain\u002FREADME.md).\n\n## 🐳 Update Docker Installation\n**For users with Docker-based MCP client configurations:**\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:latest\n```\nThe `latest` tag will always point to the most recent release.\nTo pull this specific version, run:\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:4.4.2\n```\n\n## 📦 Update DXT Extension Installation\n**For Claude Desktop users:**\n1. Download the `.dxt` file below\n2. Pre-pull the Docker image to avoid timeout issues:\n   ```bash\n   docker pull stickerdaniel\u002Flinkedin-mcp-server:4.4.2\n   ```\n3. Double-click the `.dxt` file to install in Claude Desktop\n4. Restart Claude Desktop\n\n> **Note:** The pre-pull step is important because Claude Desktop has a ~60 second connection timeout. Without pre-pulling, the initial image download may exceed this limit.\n\n\n## What's Changed\n* docs: Trim AGENTS.md to behavioral guidance, clean README Docker section by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F229\n* chore(deps): update ci dependencies by @renovate[bot] in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F226\n* docs(github): agent instructions for issues by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F241\n* Convert issue templates to GitHub forms by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F242\n* fix(rate-limit): ignore hidden recaptcha by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F244\n* chore: bump version to 4.4.2 by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F245\n\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fcompare\u002Fv4.4.1...v4.4.2","2026-03-20T22:59:30",{"id":218,"version":219,"summary_zh":220,"released_at":221},147591,"v4.4.1","For an installation guide, refer to the [README](https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fblob\u002Fmain\u002FREADME.md).\n\n## 🐳 Update Docker Installation\n**For users with Docker-based MCP client configurations:**\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:latest\n```\nThe `latest` tag will always point to the most recent release.\nTo pull this specific version, run:\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:4.4.1\n```\n\n## 📦 Update DXT Extension Installation\n**For Claude Desktop users:**\n1. Download the `.dxt` file below\n2. Pre-pull the Docker image to avoid timeout issues:\n   ```bash\n   docker pull stickerdaniel\u002Flinkedin-mcp-server:4.4.1\n   ```\n3. Double-click the `.dxt` file to install in Claude Desktop\n4. Restart Claude Desktop\n\n> **Note:** The pre-pull step is important because Claude Desktop has a ~60 second connection timeout. Without pre-pulling, the initial image download may exceed this limit.\n\n\n## What's Changed\n* fix(scraping): wait for search results content before extracting by @jonzarecki in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F225\n* chore: Bump version to 4.4.1 by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F228\n\n## New Contributors\n* @jonzarecki made their first contribution in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F225\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fcompare\u002Fv4.4.0...v4.4.1","2026-03-16T01:02:08",{"id":223,"version":224,"summary_zh":225,"released_at":226},147592,"v4.4.0","For an installation guide, refer to the [README](https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fblob\u002Fmain\u002FREADME.md).\n\n## 🐳 Update Docker Installation\n**For users with Docker-based MCP client configurations:**\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:latest\n```\nThe `latest` tag will always point to the most recent release.\nTo pull this specific version, run:\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:4.4.0\n```\n\n## 📦 Update DXT Extension Installation\n**For Claude Desktop users:**\n1. Download the `.dxt` file below\n2. Pre-pull the Docker image to avoid timeout issues:\n   ```bash\n   docker pull stickerdaniel\u002Flinkedin-mcp-server:4.4.0\n   ```\n3. Double-click the `.dxt` file to install in Claude Desktop\n4. Restart Claude Desktop\n\n> **Note:** The pre-pull step is important because Claude Desktop has a ~60 second connection timeout. Without pre-pulling, the initial image download may exceed this limit.\n\n\n## What's Changed\n* chore(deps): update all major dependencies (major) by @renovate[bot] in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F208\n* chore(deps): update ci dependencies by @renovate[bot] in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F207\n* docs(README): installation link for uv in README by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F214\n* feat(server): serialize tool calls by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F219\n* Feature\u002F220 docker bridge debug by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F221\n* chore: Bump version to 4.4.0 by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F222\n\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fcompare\u002Fv4.3.0...v4.4.0","2026-03-13T10:43:00",{"id":228,"version":229,"summary_zh":230,"released_at":231},147593,"v4.3.0","For an installation guide, refer to the [README](https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fblob\u002Fmain\u002FREADME.md).\n\n## 🐳 Update Docker Installation\n**For users with Docker-based MCP client configurations:**\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:latest\n```\nThe `latest` tag will always point to the most recent release.\nTo pull this specific version, run:\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:4.3.0\n```\n\n## 📦 Update DXT Extension Installation\n**For Claude Desktop users:**\n1. Download the `.dxt` file below\n2. Pre-pull the Docker image to avoid timeout issues:\n   ```bash\n   docker pull stickerdaniel\u002Flinkedin-mcp-server:4.3.0\n   ```\n3. Double-click the `.dxt` file to install in Claude Desktop\n4. Restart Claude Desktop\n\n> **Note:** The pre-pull step is important because Claude Desktop has a ~60 second connection timeout. Without pre-pulling, the initial image download may exceed this limit.\n\n\n## What's Changed\n* feat(scraping): add compact references by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F206\n* chore: Bump version to 4.3.0 by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F210\n\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fcompare\u002Fv4.2.0...v4.3.0","2026-03-09T10:00:43",{"id":233,"version":234,"summary_zh":235,"released_at":236},147594,"v4.2.0","For an installation guide, refer to the [README](https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fblob\u002Fmain\u002FREADME.md).\n\n## 🐳 Update Docker Installation\n**For users with Docker-based MCP client configurations:**\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:latest\n```\nThe `latest` tag will always point to the most recent release.\nTo pull this specific version, run:\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:4.2.0\n```\n\n## 📦 Update DXT Extension Installation\n**For Claude Desktop users:**\n1. Download the `.dxt` file below\n2. Pre-pull the Docker image to avoid timeout issues:\n   ```bash\n   docker pull stickerdaniel\u002Flinkedin-mcp-server:4.2.0\n   ```\n3. Double-click the `.dxt` file to install in Claude Desktop\n4. Restart Claude Desktop\n\n> **Note:** The pre-pull step is important because Claude Desktop has a ~60 second connection timeout. Without pre-pulling, the initial image download may exceed this limit.\n\n\n## What's Changed\n* chore(deps): update ci dependencies by @renovate[bot] in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F165\n* docs(contributing): add CONTRIBUTING.md with contributor checklists by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F178\n* feat(tools): add posts section to get_person_profile by @ConnorMoss02 in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F168\n* refactor(scraping): replace Flag enums with config dicts by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F184\n* docs: sync manifest.json tools and features with current capabilities by @ConnorMoss02 in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F183\n* chore(deps): lock file maintenance by @renovate[bot] in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F166\n* chore(deps): bump fastmcp constraint to >=3.0.0 by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F191\n* refactor(error-handler): replace handle_tool_error with ToolError by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F192\n* refactor(tools): Use Depends() to inject extractor by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F194\n* chore(config): Update model and provider settings in btca.config.jsonc by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F196\n* refactor(tools): Simplify annotations to dict syntax and add tags by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F198\n* refactor(server): Split lifespan into composable browser + auth lifespans by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F199\n* feat(tools): add global 90s tool timeouts by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F197\n* feat(tools): add job IDs, sidebar scrolling, and pagination to search_jobs by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F200\n* docs(AGENTS): add section for verifying bug reports with detailed curl commands by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F202\n* fix(scraping): Wait for activity feed content before extracting by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F203\n* chore: Bump version to 4.2.0 by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F204\n\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fcompare\u002Fv4.1.2...v4.2.0","2026-03-05T23:39:24",{"id":238,"version":239,"summary_zh":240,"released_at":241},147595,"v4.1.2","For an installation guide, refer to the [README](https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fblob\u002Fmain\u002FREADME.md).\n\n## 🐳 Update Docker Installation\n**For users with Docker-based MCP client configurations:**\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:latest\n```\nThe `latest` tag will always point to the most recent release.\nTo pull this specific version, run:\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:4.1.2\n```\n\n## 📦 Update DXT Extension Installation\n**For Claude Desktop users:**\n1. Download the `.dxt` file below\n2. Pre-pull the Docker image to avoid timeout issues:\n   ```bash\n   docker pull stickerdaniel\u002Flinkedin-mcp-server:4.1.2\n   ```\n3. Double-click the `.dxt` file to install in Claude Desktop\n4. Restart Claude Desktop\n\n> **Note:** The pre-pull step is important because Claude Desktop has a ~60 second connection timeout. Without pre-pulling, the initial image download may exceed this limit.\n\n\n## What's Changed\n* chore(deps): update ci dependencies by @renovate[bot] in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F153\n* chore(deps): lock file maintenance by @renovate[bot] in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F154\n* fix(cli): polish stdio startup flow by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F156\n* feat(tools): add search_people tool by @ConnorMoss02 in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F157\n* chore: bump version to 4.1.0 by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F158\n* ci(release): fix workflow blocked by branch protection by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F159\n* chore: bump version to 4.1.1 by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F161\n* fix(release): avoid YAML heredoc issue in restore step by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F162\n* fix(release): use PAT for branch protection API calls by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F163\n\n## New Contributors\n* @ConnorMoss02 made their first contribution in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F157\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fcompare\u002Fv4.0.0...v4.1.2","2026-02-20T18:53:22",{"id":243,"version":244,"summary_zh":245,"released_at":246},147596,"v4.0.0","For an installation guide, refer to the [README](https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fblob\u002Fmain\u002FREADME.md).\n\n## 🐳 Update Docker Installation\n**For users with Docker-based MCP client configurations:**\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:latest\n```\nThe `latest` tag will always point to the most recent release.\nTo pull this specific version, run:\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:4.0.0\n```\n\n## 📦 Update DXT Extension Installation\n**For Claude Desktop users:**\n1. Download the `.dxt` file below\n2. Pre-pull the Docker image to avoid timeout issues:\n   ```bash\n   docker pull stickerdaniel\u002Flinkedin-mcp-server:4.0.0\n   ```\n3. Double-click the `.dxt` file to install in Claude Desktop\n4. Restart Claude Desktop\n\n> **Note:** The pre-pull step is important because Claude Desktop has a ~60 second connection timeout. Without pre-pulling, the initial image download may exceed this limit.\n\n\n## What's Changed\n* 02-16-feat_scraper_refactored_scraping_tools_to_use_innertext_extraction_with_configurable_section_selection_for_person_company_and_job_profiles._removed_dependency_on_linkedin-scraper_and_integrated_core_functionalities_directly._enh by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F155\n\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fcompare\u002Fv3.0.4...v4.0.0","2026-02-16T14:00:59",{"id":248,"version":249,"summary_zh":250,"released_at":251},147597,"v3.0.4","For an installation guide, refer to the [README](https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fblob\u002Fmain\u002FREADME.md).\n\n## 🐳 Update Docker Installation\n**For users with Docker-based MCP client configurations:**\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:latest\n```\nThe `latest` tag will always point to the most recent release.\nTo pull this specific version, run:\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:3.0.4\n```\n\n## 📦 Update DXT Extension Installation\n**For Claude Desktop users:**\n1. Download the `.dxt` file below\n2. Pre-pull the Docker image to avoid timeout issues:\n   ```bash\n   docker pull stickerdaniel\u002Flinkedin-mcp-server:3.0.4\n   ```\n3. Double-click the `.dxt` file to install in Claude Desktop\n4. Restart Claude Desktop\n\n> **Note:** The pre-pull step is important because Claude Desktop has a ~60 second connection timeout. Without pre-pulling, the initial image download may exceed this limit.\n\n\n## What's Changed\n* fix(docker): copy profile to temp dir for cross-platform cookie bridge by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F150\n* chore: bump version to 3.0.4 by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F151\n\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fcompare\u002Fv3.0.3...v3.0.4","2026-02-13T17:23:11",{"id":253,"version":254,"summary_zh":255,"released_at":256},147598,"v3.0.3","For an installation guide, refer to the [README](https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fblob\u002Fmain\u002FREADME.md).\n\n## 🐳 Update Docker Installation\n**For users with Docker-based MCP client configurations:**\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:latest\n```\nThe `latest` tag will always point to the most recent release.\nTo pull this specific version, run:\n```bash\ndocker pull stickerdaniel\u002Flinkedin-mcp-server:3.0.3\n```\n\n## 📦 Update DXT Extension Installation\n**For Claude Desktop users:**\n1. Download the `.dxt` file below\n2. Pre-pull the Docker image to avoid timeout issues:\n   ```bash\n   docker pull stickerdaniel\u002Flinkedin-mcp-server:3.0.3\n   ```\n3. Double-click the `.dxt` file to install in Claude Desktop\n4. Restart Claude Desktop\n\n> **Note:** The pre-pull step is important because Claude Desktop has a ~60 second connection timeout. Without pre-pulling, the initial image download may exceed this limit.\n\n\n## What's Changed\n* feat: add cookie bridge for cross-platform Docker portability by @stickerdaniel in https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fpull\u002F149\n\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fstickerdaniel\u002Flinkedin-mcp-server\u002Fcompare\u002Fv3.0.2...v3.0.3","2026-02-13T15:05:54"]