[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-neo4j-contrib--mcp-neo4j":3,"tool-neo4j-contrib--mcp-neo4j":65},[4,23,32,40,48,57],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":22},2268,"ML-For-Beginners","microsoft\u002FML-For-Beginners","ML-For-Beginners 是由微软推出的一套系统化机器学习入门课程，旨在帮助零基础用户轻松掌握经典机器学习知识。这套课程将学习路径规划为 12 周，包含 26 节精炼课程和 52 道配套测验，内容涵盖从基础概念到实际应用的完整流程，有效解决了初学者面对庞大知识体系时无从下手、缺乏结构化指导的痛点。\n\n无论是希望转型的开发者、需要补充算法背景的研究人员，还是对人工智能充满好奇的普通爱好者，都能从中受益。课程不仅提供了清晰的理论讲解，还强调动手实践，让用户在循序渐进中建立扎实的技能基础。其独特的亮点在于强大的多语言支持，通过自动化机制提供了包括简体中文在内的 50 多种语言版本，极大地降低了全球不同背景用户的学习门槛。此外，项目采用开源协作模式，社区活跃且内容持续更新，确保学习者能获取前沿且准确的技术资讯。如果你正寻找一条清晰、友好且专业的机器学习入门之路，ML-For-Beginners 将是理想的起点。",84991,2,"2026-04-05T10:45:23",[13,14,15,16,17,18,19,20,21],"图像","数据工具","视频","插件","Agent","其他","语言模型","开发框架","音频","ready",{"id":24,"name":25,"github_repo":26,"description_zh":27,"stars":28,"difficulty_score":29,"last_commit_at":30,"category_tags":31,"status":22},2234,"scikit-learn","scikit-learn\u002Fscikit-learn","scikit-learn 是一个基于 Python 构建的开源机器学习库，依托于 SciPy、NumPy 等科学计算生态，旨在让机器学习变得简单高效。它提供了一套统一且简洁的接口，涵盖了从数据预处理、特征工程到模型训练、评估及选择的全流程工具，内置了包括线性回归、支持向量机、随机森林、聚类等在内的丰富经典算法。\n\n对于希望快速验证想法或构建原型的数据科学家、研究人员以及 Python 开发者而言，scikit-learn 是不可或缺的基础设施。它有效解决了机器学习入门门槛高、算法实现复杂以及不同模型间调用方式不统一的痛点，让用户无需重复造轮子，只需几行代码即可调用成熟的算法解决分类、回归、聚类等实际问题。\n\n其核心技术亮点在于高度一致的 API 设计风格，所有估算器（Estimator）均遵循相同的调用逻辑，极大地降低了学习成本并提升了代码的可读性与可维护性。此外，它还提供了强大的模型选择与评估工具，如交叉验证和网格搜索，帮助用户系统地优化模型性能。作为一个由全球志愿者共同维护的成熟项目，scikit-learn 以其稳定性、详尽的文档和活跃的社区支持，成为连接理论学习与工业级应用的最",65628,1,"2026-04-05T10:10:46",[20,18,14],{"id":33,"name":34,"github_repo":35,"description_zh":36,"stars":37,"difficulty_score":10,"last_commit_at":38,"category_tags":39,"status":22},3364,"keras","keras-team\u002Fkeras","Keras 是一个专为人类设计的深度学习框架，旨在让构建和训练神经网络变得简单直观。它解决了开发者在不同深度学习后端之间切换困难、模型开发效率低以及难以兼顾调试便捷性与运行性能的痛点。\n\n无论是刚入门的学生、专注算法的研究人员，还是需要快速落地产品的工程师，都能通过 Keras 轻松上手。它支持计算机视觉、自然语言处理、音频分析及时间序列预测等多种任务。\n\nKeras 3 的核心亮点在于其独特的“多后端”架构。用户只需编写一套代码，即可灵活选择 TensorFlow、JAX、PyTorch 或 OpenVINO 作为底层运行引擎。这一特性不仅保留了 Keras 一贯的高层易用性，还允许开发者根据需求自由选择：利用 JAX 或 PyTorch 的即时执行模式进行高效调试，或切换至速度最快的后端以获得最高 350% 的性能提升。此外，Keras 具备强大的扩展能力，能无缝从本地笔记本电脑扩展至大规模 GPU 或 TPU 集群，是连接原型开发与生产部署的理想桥梁。",63927,"2026-04-04T15:24:37",[20,14,18],{"id":41,"name":42,"github_repo":43,"description_zh":44,"stars":45,"difficulty_score":10,"last_commit_at":46,"category_tags":47,"status":22},2403,"crawl4ai","unclecode\u002Fcrawl4ai","Crawl4AI 是一款专为大语言模型（LLM）设计的开源网络爬虫与数据提取工具。它的核心使命是将纷繁复杂的网页内容转化为干净、结构化的 Markdown 格式，直接服务于检索增强生成（RAG）、智能体构建及各类数据管道，让 AI 能更轻松地“读懂”互联网。\n\n传统爬虫往往面临反爬机制拦截、动态内容加载困难以及输出格式杂乱等痛点，导致后续数据处理成本高昂。Crawl4AI 通过内置自动化的三级反机器人检测、代理升级策略以及对 Shadow DOM 的深度支持，有效突破了这些障碍。它能智能移除同意弹窗，处理深层链接，并具备长任务崩溃恢复能力，确保数据采集的稳定与高效。\n\n这款工具特别适合开发者、AI 研究人员及数据工程师使用。无论是需要为本地模型构建知识库，还是搭建大规模自动化信息采集流程，Crawl4AI 都提供了极高的可控性与灵活性。作为 GitHub 上备受瞩目的开源项目，它完全免费开放，无需繁琐的注册或昂贵的 API 费用，让用户能够专注于数据价值本身而非采集难题。",63242,"2026-04-02T22:29:19",[14,17],{"id":49,"name":50,"github_repo":51,"description_zh":52,"stars":53,"difficulty_score":54,"last_commit_at":55,"category_tags":56,"status":22},4243,"MinerU","opendatalab\u002FMinerU","MinerU 是一款专为大语言模型（LLM）打造的文档解析工具，旨在将复杂的 PDF 文件高效转化为机器易读的 Markdown 或 JSON 格式。在日常工作中，许多用户面临从扫描版论文、技术手册或包含复杂排版的文档中提取高质量文本的难题，传统方法往往难以保留原有的公式、表格和结构信息，导致后续 AI 处理效果不佳。MinerU 正是为了解决这一痛点而生，它能精准识别并还原文档中的多栏布局、数学公式及图表内容，确保输出数据干净、结构化，直接适配各类智能体（Agentic）工作流。\n\n这款工具特别适合开发者、数据科学家以及需要构建知识库的研究人员使用。无论是希望微调专属模型的算法工程师，还是试图搭建企业级 RAG（检索增强生成）系统的技术团队，MinerU 都能提供强有力的支持。其核心技术亮点在于对复杂版面分析的深度优化，不仅支持批量处理，还能在保持高准确率的同时，大幅降低数据清洗的人力成本。通过 MinerU，用户可以轻松打通从原始文档到 AI 应用的数据链路，让非结构化文档真正变成可被智能体理解的高价值资产。",58197,3,"2026-04-06T01:37:49",[13,14,18,20,19],{"id":58,"name":59,"github_repo":60,"description_zh":61,"stars":62,"difficulty_score":10,"last_commit_at":63,"category_tags":64,"status":22},193,"meilisearch","meilisearch\u002Fmeilisearch","Meilisearch 是一个开源的极速搜索服务，专为现代应用和网站打造，开箱即用。它能帮助开发者快速集成高质量的搜索功能，无需复杂的配置或额外的数据预处理。传统搜索方案往往需要大量调优才能实现准确结果，而 Meilisearch 内置了拼写容错、同义词识别、即时响应等实用特性，并支持 AI 驱动的混合搜索（结合关键词与语义理解），显著提升用户查找信息的体验。\n\nMeilisearch 特别适合 Web 开发者、产品团队或初创公司使用，尤其适用于需要快速上线搜索功能的场景，如电商网站、内容平台或 SaaS 应用。它提供简洁的 RESTful API 和多种语言 SDK，部署简单，资源占用低，本地开发或生产环境均可轻松运行。对于希望在不依赖大型云服务的前提下，为用户提供流畅、智能搜索体验的团队来说，Meilisearch 是一个高效且友好的选择。",56972,"2026-04-05T22:34:33",[13,17,14,20,16,18],{"id":66,"github_repo":67,"name":68,"description_en":69,"description_zh":70,"ai_summary_zh":71,"readme_en":72,"readme_zh":73,"quickstart_zh":74,"use_case_zh":75,"hero_image_url":76,"owner_login":77,"owner_name":78,"owner_avatar_url":79,"owner_bio":80,"owner_company":81,"owner_location":81,"owner_email":81,"owner_twitter":81,"owner_website":82,"owner_url":83,"languages":84,"stars":101,"forks":102,"last_commit_at":103,"license":104,"difficulty_score":105,"env_os":106,"env_gpu":107,"env_ram":106,"env_deps":108,"category_tags":113,"github_topics":114,"view_count":10,"oss_zip_url":81,"oss_zip_packed_at":81,"status":22,"created_at":120,"updated_at":121,"faqs":122,"releases":152},2311,"neo4j-contrib\u002Fmcp-neo4j","mcp-neo4j","Neo4j Labs Model Context Protocol servers","mcp-neo4j 是 Neo4j Labs 推出的一组开源服务器，旨在通过模型上下文协议（MCP）将大语言模型与 Neo4j 图数据库及 Aura 云服务无缝连接。它让用户能直接用自然语言与图数据库交互，无需手动编写复杂的查询代码，从而轻松实现数据检索、图表生成、实例管理甚至个人知识记忆存储等功能。\n\n这套工具主要解决了 AI 助手难以直接操作专业数据库和云资源的痛点。通过它，用户可以在 Claude Desktop、VS Code 或 Cursor 等常用编辑器中，用对话方式完成“查询销量最高的产品”、“创建新的云数据库实例”或“记录工作日志”等任务，大幅降低了图技术的使用门槛。\n\nmcp-neo4j 特别适合开发者、数据工程师以及希望探索图数据库能力的 AI 应用构建者。其核心亮点在于提供了四个专用服务模块：支持自然语言转 Cypher 查询、基于图结构的长期记忆存储、Aura 云平台的全生命周期管理，以及交互式的数据建模与可视化。此外，它灵活支持本地 STDIO、SSE 及 HTTP 多种传输模式，并原生提供容器化方案，便于在 AWS 或 Azure 等云端环境中快速部署和扩展","mcp-neo4j 是 Neo4j Labs 推出的一组开源服务器，旨在通过模型上下文协议（MCP）将大语言模型与 Neo4j 图数据库及 Aura 云服务无缝连接。它让用户能直接用自然语言与图数据库交互，无需手动编写复杂的查询代码，从而轻松实现数据检索、图表生成、实例管理甚至个人知识记忆存储等功能。\n\n这套工具主要解决了 AI 助手难以直接操作专业数据库和云资源的痛点。通过它，用户可以在 Claude Desktop、VS Code 或 Cursor 等常用编辑器中，用对话方式完成“查询销量最高的产品”、“创建新的云数据库实例”或“记录工作日志”等任务，大幅降低了图技术的使用门槛。\n\nmcp-neo4j 特别适合开发者、数据工程师以及希望探索图数据库能力的 AI 应用构建者。其核心亮点在于提供了四个专用服务模块：支持自然语言转 Cypher 查询、基于图结构的长期记忆存储、Aura 云平台的全生命周期管理，以及交互式的数据建模与可视化。此外，它灵活支持本地 STDIO、SSE 及 HTTP 多种传输模式，并原生提供容器化方案，便于在 AWS 或 Azure 等云端环境中快速部署和扩展。作为实验性项目，它由社区共同维护，为前沿的 AI 与图技术融合提供了丰富的探索空间。","# Neo4j Labs MCP Servers\n\n## Neo4j Labs\n\nThese MCP servers are a part of the [Neo4j Labs](https:\u002F\u002Fneo4j.com\u002Flabs\u002F) program. \nThey are developed and maintained by the Neo4j Field GenAI team and welcome contributions from the larger developer community. \nThese servers are frequently updated with new and experimental features, but are not supported by the Neo4j product team. \n\n**They are actively developed and maintained, but we don’t provide any SLAs or guarantees around backwards compatibility and deprecation.**\n\nIf you are looking for the official product Neo4j MCP server please find it [here](https:\u002F\u002Fgithub.com\u002Fneo4j\u002Fmcp).\n\n## Overview\n\nModel Context Protocol (MCP) is a [standardized protocol](https:\u002F\u002Fmodelcontextprotocol.io\u002Fintroduction) for managing context between large language models (LLMs) and external systems. \n\nThis lets you use Claude Desktop, or any other MCP Client (VS Code, Cursor, Windsurf, Gemini CLI), to use natural language to accomplish things with Neo4j and your Aura account, e.g.:\n\n* What is in this graph?\n* Render a chart from the top products sold by frequency, total and average volume\n* List my instances\n* Create a new instance named mcp-test for Aura Professional with 4GB and Graph Data Science enabled\n* Store the fact that I worked on the Neo4j MCP Servers today with Andreas and Oskar\n\n## Servers\n\n### `mcp-neo4j-cypher` - natural language to Cypher queries\n\n[Details in Readme](.\u002Fservers\u002Fmcp-neo4j-cypher\u002F)\n\nGet database schema for a configured database and execute generated read and write Cypher queries on that database.\n\n**Requirement**: Requires the [APOC plugin](https:\u002F\u002Fneo4j.com\u002Fdocs\u002Fapoc\u002Fcurrent\u002Finstallation\u002F) to be installed and enabled on the Neo4j instance for schema inspection.\n\n### `mcp-neo4j-memory` - knowledge graph memory stored in Neo4j\n\n[Details in Readme](.\u002Fservers\u002Fmcp-neo4j-memory\u002F)\n\nStore and retrieve entities and relationships from your personal knowledge graph in a local or remote Neo4j instance.\nAccess that information over different sessions, conversations, clients.\n\n### `mcp-neo4j-cloud-aura-api` - Neo4j Aura cloud service management API\n\n[Details in Readme](.\u002Fservers\u002Fmcp-neo4j-cloud-aura-api\u002F\u002F)\n\nManage your [Neo4j Aura](https:\u002F\u002Fconsole.neo4j.io) instances directly from the comfort of your AI assistant chat.\n\nCreate and destroy instances, find instances by name, scale them up and down and enable features.\n\n### `mcp-neo4j-data-modeling` - interactive graph data modeling and visualization\n\n[Details in Readme](.\u002Fservers\u002Fmcp-neo4j-data-modeling\u002F)\n\nCreate, validate, and visualize Neo4j graph data models. Allows for model import\u002Fexport from Arrows.app.\n\n## Transport Modes\n\nAll servers support multiple transport modes:\n\n- **STDIO** (default): Standard input\u002Foutput for local tools and Claude Desktop integration\n- **SSE**: Server-Sent Events for web-based deployments\n- **HTTP**: Streamable HTTP for modern web deployments and microservices\n\n### HTTP Transport Configuration\n\nTo run a server in HTTP mode, use the `--transport http` flag:\n\n```bash\n# Basic HTTP mode\nmcp-neo4j-cypher --transport http\n\n# Custom HTTP configuration\nmcp-neo4j-cypher --transport http --host 127.0.0.1 --port 8080 --path \u002Fapi\u002Fmcp\u002F\n```\n\nEnvironment variables are also supported:\n\n```bash\nexport NEO4J_TRANSPORT=http\nexport NEO4J_MCP_SERVER_HOST=127.0.0.1\nexport NEO4J_MCP_SERVER_PORT=8080\nexport NEO4J_MCP_SERVER_PATH=\u002Fapi\u002Fmcp\u002F\nmcp-neo4j-cypher\n```\n\n## Cloud Deployment\n\nAll servers in this repository are containerized and ready for cloud deployment on platforms like AWS ECS Fargate and Azure Container Apps. Each server supports HTTP transport mode specifically designed for scalable, production-ready deployments with auto-scaling and load balancing capabilities.\n\n📋 **[Complete Cloud Deployment Guide →](README-Cloud.md)**\n\nThe deployment guide covers:\n- **AWS ECS Fargate**: Step-by-step deployment with auto-scaling and Application Load Balancer\n- **Azure Container Apps**: Serverless container deployment with built-in scaling and traffic management\n- **Configuration Best Practices**: Security, monitoring, resource recommendations, and troubleshooting\n- **Integration Examples**: Connecting MCP clients to cloud-deployed servers\n\n## Contributing\n\nContributions are welcome! Please feel free to submit a Pull Request.\n\n## Blog Posts\n\n* [Everything a Developer Needs to Know About the Model Context Protocol (MCP)](https:\u002F\u002Fneo4j.com\u002Fblog\u002Fdeveloper\u002Fmodel-context-protocol\u002F)\n* [Claude Converses With Neo4j Via MCP - Graph Database & Analytics](https:\u002F\u002Fneo4j.com\u002Fblog\u002Fdeveloper\u002Fclaude-converses-neo4j-via-mcp\u002F)\n* [Building Knowledge Graphs With Claude and Neo4j: A No-Code MCP Approach - Graph Database & Analytics](https:\u002F\u002Fneo4j.com\u002Fblog\u002Fdeveloper\u002Fknowledge-graphs-claude-neo4j-mcp\u002F)\n* [Using the Neo4j Extension in Gemini CLI](https:\u002F\u002Fcloud.google.com\u002Fblog\u002Ftopics\u002Fdevelopers-practitioners\u002Fusing-the-neo4j-extension-in-gemini-cli)\n\n## License\n\nMIT License\n","# Neo4j Labs MCP 服务器\n\n## Neo4j Labs\n\n这些 MCP 服务器是 [Neo4j Labs](https:\u002F\u002Fneo4j.com\u002Flabs\u002F) 计划的一部分。\n它们由 Neo4j 的现场生成式 AI 团队开发和维护，并欢迎更广泛的开发者社区贡献代码。\n这些服务器会频繁更新，加入新的实验性功能，但并不受 Neo4j 产品团队的支持。\n\n**它们正在积极开发和维护中，但我们不提供任何服务级别协议（SLA）或关于向后兼容性和弃用的保证。**\n\n如果您正在寻找官方的 Neo4j MCP 服务器，请访问 [这里](https:\u002F\u002Fgithub.com\u002Fneo4j\u002Fmcp)。\n\n## 概述\n\n模型上下文协议（MCP）是一种用于管理大型语言模型（LLM）与外部系统之间上下文的[标准化协议](https:\u002F\u002Fmodelcontextprotocol.io\u002Fintroduction)。\n\n这使您可以使用 Claude Desktop 或其他 MCP 客户端（VS Code、Cursor、Windsurf、Gemini CLI），通过自然语言与 Neo4j 和您的 Aura 账户交互，完成各种任务，例如：\n\n* 这个图里有什么？\n* 根据频率、总量和平均量绘制销售前几名产品的图表\n* 列出我的实例\n* 在 Aura Professional 中创建一个名为 mcp-test 的新实例，配置 4GB 内存并启用 Graph Data Science 功能\n* 存储今天我和 Andreas 以及 Oskar 一起参与了 Neo4j MCP 服务器开发的事实\n\n## 服务器\n\n### `mcp-neo4j-cypher` - 自然语言到 Cypher 查询\n\n[详细信息请参阅 README](.\u002Fservers\u002Fmcp-neo4j-cypher\u002F)\n\n获取已配置数据库的模式，并在该数据库上执行生成的读写 Cypher 查询。\n\n**要求**：需要在 Neo4j 实例上安装并启用 [APOC 插件](https:\u002F\u002Fneo4j.com\u002Fdocs\u002Fapoc\u002Fcurrent\u002Finstallation\u002F)，以便进行模式检查。\n\n### `mcp-neo4j-memory` - 存储在 Neo4j 中的知识图谱记忆\n\n[详细信息请参阅 README](.\u002Fservers\u002Fmcp-neo4j-memory\u002F)\n\n在本地或远程 Neo4j 实例中存储和检索您个人知识图谱中的实体和关系。\n可以在不同的会话、对话和客户端之间访问这些信息。\n\n### `mcp-neo4j-cloud-aura-api` - Neo4j Aura 云服务管理 API\n\n[详细信息请参阅 README](.\u002Fservers\u002Fmcp-neo4j-cloud-aura-api\u002F\u002F)\n\n直接从您的 AI 助手聊天界面中管理您的 [Neo4j Aura](https:\u002F\u002Fconsole.neo4j.io) 实例。\n可以创建和销毁实例，按名称查找实例，调整实例规模，并启用相关功能。\n\n### `mcp-neo4j-data-modeling` - 交互式图数据建模与可视化\n\n[详细信息请参阅 README](.\u002Fservers\u002Fmcp-neo4j-data-modeling\u002F)\n\n创建、验证和可视化 Neo4j 图数据模型。支持从 Arrows.app 导入和导出模型。\n\n## 传输模式\n\n所有服务器都支持多种传输模式：\n\n- **STDIO**（默认）：用于本地工具和 Claude Desktop 集成的标准输入输出\n- **SSE**：用于基于 Web 的部署的服务器发送事件\n- **HTTP**：适用于现代 Web 部署和微服务的可流式 HTTP\n\n### HTTP 传输配置\n\n要以 HTTP 模式运行服务器，请使用 `--transport http` 标志：\n\n```bash\n# 基本 HTTP 模式\nmcp-neo4j-cypher --transport http\n\n# 自定义 HTTP 配置\nmcp-neo4j-cypher --transport http --host 127.0.0.1 --port 8080 --path \u002Fapi\u002Fmcp\u002F\n```\n\n也可以使用环境变量：\n\n```bash\nexport NEO4J_TRANSPORT=http\nexport NEO4J_MCP_SERVER_HOST=127.0.0.1\nexport NEO4J_MCP_SERVER_PORT=8080\nexport NEO4J_MCP_SERVER_PATH=\u002Fapi\u002Fmcp\u002F\nmcp-neo4j-cypher\n```\n\n## 云部署\n\n此仓库中的所有服务器都已容器化，可直接部署到 AWS ECS Fargate 和 Azure Container Apps 等云平台上。每台服务器都支持专为可扩展、生产就绪的部署设计的 HTTP 传输模式，具备自动伸缩和负载均衡能力。\n\n📋 **[完整云部署指南 →](README-Cloud.md)**\n\n部署指南涵盖：\n- **AWS ECS Fargate**：带自动伸缩和应用负载均衡器的分步部署\n- **Azure Container Apps**：内置扩展和流量管理的无服务器容器部署\n- **配置最佳实践**：安全性、监控、资源建议和故障排除\n- **集成示例**：将 MCP 客户端连接到云端部署的服务器\n\n## 贡献\n\n欢迎贡献！请随时提交 Pull Request。\n\n## 博客文章\n\n* [开发者需要了解的关于模型上下文协议（MCP）的一切](https:\u002F\u002Fneo4j.com\u002Fblog\u002Fdeveloper\u002Fmodel-context-protocol\u002F)\n* [Claude 通过 MCP 与 Neo4j 对话——图数据库与分析](https:\u002F\u002Fneo4j.com\u002Fblog\u002Fdeveloper\u002Fclaude-converses-neo4j-via-mcp\u002F)\n* [使用 Claude 和 Neo4j 构建知识图谱：无代码 MCP 方法——图数据库与分析](https:\u002F\u002Fneo4j.com\u002Fblog\u002Fdeveloper\u002Fknowledge-graphs-claude-neo4j-mcp\u002F)\n* [在 Gemini CLI 中使用 Neo4j 扩展](https:\u002F\u002Fcloud.google.com\u002Fblog\u002Ftopics\u002Fdevelopers-practitioners\u002Fusing-the-neo4j-extension-in-gemini-cli)\n\n## 许可证\n\nMIT 许可证","# mcp-neo4j 快速上手指南\n\nmcp-neo4j 是 Neo4j Labs 推出的一套基于模型上下文协议（MCP）的服务器工具集，旨在让大语言模型（如 Claude、Gemini 等）通过自然语言与 Neo4j 数据库及 Aura 云服务进行交互。\n\n## 环境准备\n\n### 系统要求\n- **操作系统**：Linux, macOS, 或 Windows (WSL2 推荐)\n- **运行时环境**：Node.js (v18 或更高版本) 或 Python (视具体实现语言而定，通常 MCP 服务器多为 Node\u002FPython)\n- **Neo4j 实例**：\n    - 本地运行的 Neo4j 数据库，或\n    - Neo4j Aura 云实例\n- **前置依赖**：\n    - 若使用 `mcp-neo4j-cypher` 进行模式检查，必须在 Neo4j 实例中安装并启用 **APOC 插件**。\n    - 一个支持 MCP 协议的客户端（如 Claude Desktop, Cursor, VS Code, Windsurf 等）。\n\n### 网络与权限\n- 确保运行 MCP 服务器的机器可以访问 Neo4j 数据库端口（默认 7687）和管理端口（默认 7474）。\n- 准备好 Neo4j 的连接凭证（URI, 用户名，密码）。\n\n## 安装步骤\n\n由于该仓库包含多个独立的 MCP 服务器，您可以根据需求选择安装特定的服务。以下以常用的 `mcp-neo4j-cypher` 为例（假设该项目通过 npm 发布，若为源码运行请参考下方源码方式）。\n\n### 方式一：通过包管理器安装（推荐）\n\n如果项目已发布到 npm：\n\n```bash\nnpm install -g @neo4j\u002Fmcp-neo4j-cypher\n# 或者针对其他模块\nnpm install -g @neo4j\u002Fmcp-neo4j-memory\nnpm install -g @neo4j\u002Fmcp-neo4j-cloud-aura-api\nnpm install -g @neo4j\u002Fmcp-neo4j-data-modeling\n```\n\n*注：若国内访问 npm 较慢，可配置淘宝镜像源：*\n```bash\nnpm config set registry https:\u002F\u002Fregistry.npmmirror.com\n```\n\n### 方式二：从源码运行\n\n克隆仓库并安装依赖：\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fneo4j-labs\u002Fmcp-neo4j.git\ncd mcp-neo4j\n\n# 进入具体服务器目录，例如 cypher 服务器\ncd servers\u002Fmcp-neo4j-cypher\n\n# 安装依赖\nnpm install\n# 或者如果是 python 项目\npip install -r requirements.txt\n```\n\n## 基本使用\n\n### 1. 配置环境变量\n\n在运行服务器前，需设置 Neo4j 连接信息。以 `mcp-neo4j-cypher` 为例：\n\n```bash\nexport NEO4J_URI=neo4j:\u002F\u002Flocalhost:7687\nexport NEO4J_USERNAME=neo4j\nexport NEO4J_PASSWORD=your_password\n# 如果使用 Aura 或特定配置，可能还需要设置其他变量\n```\n\n### 2. 启动服务器\n\n#### 本地模式 (STDIO)\n适用于直接配合 Claude Desktop 或本地调试：\n\n```bash\nnpx @neo4j\u002Fmcp-neo4j-cypher\n# 或者源码运行\nnode index.js\n```\n\n#### HTTP 模式\n适用于远程部署或微服务架构：\n\n```bash\n# 使用命令行参数\nnpx @neo4j\u002Fmcp-neo4j-cypher --transport http --host 0.0.0.0 --port 8080\n\n# 或使用环境变量\nexport NEO4J_TRANSPORT=http\nexport NEO4J_MCP_SERVER_PORT=8080\nnpx @neo4j\u002Fmcp-neo4j-cypher\n```\n\n### 3. 连接 MCP 客户端\n\n以 **Claude Desktop** 为例，修改其配置文件（通常位于 `~\u002FLibrary\u002FApplication Support\u002FClaude\u002Fclaude_desktop_config.json` 或 `%APPDATA%\\Claude\\claude_desktop_config.json`），添加如下配置：\n\n```json\n{\n  \"mcpServers\": {\n    \"neo4j-cypher\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@neo4j\u002Fmcp-neo4j-cypher\"],\n      \"env\": {\n        \"NEO4J_URI\": \"neo4j:\u002F\u002Flocalhost:7687\",\n        \"NEO4J_USERNAME\": \"neo4j\",\n        \"NEO4J_PASSWORD\": \"your_password\"\n      }\n    }\n  }\n}\n```\n\n*如果是 HTTP 模式部署，客户端配置需指向对应的 SSE 或 HTTP 端点。*\n\n### 4. 开始对话\n\n重启 Claude Desktop 或其他 MCP 客户端后，即可在对话框中使用自然语言操作 Neo4j：\n\n- **查询数据**：\"What is in this graph?\"（图中有什么？）\n- **生成图表**：\"Render a chart from the top products sold by frequency.\"（按频率绘制最畅销产品的图表。）\n- **管理云资源**（需配置 aura-api 服务器）：\"Create a new instance named mcp-test for Aura Professional with 4GB.\"（创建一个名为 mcp-test 的 4GB Aura 专业版实例。）\n- **记忆存储**（需配置 memory 服务器）：\"Store the fact that I worked on the Neo4j MCP Servers today.\"（记录我今天参与了 Neo4j MCP 服务器的工作。）\n\n---\n**注意**：本工具集由 Neo4j Field GenAI 团队维护，属于实验性项目，不提供生产环境的 SLA 保证，且可能存在向后兼容性变更。如需官方支持版本，请访问 Neo4j 官方 MCP 服务器仓库。","某电商数据团队需要快速分析用户购买行为图谱，并动态调整云数据库资源以应对促销流量高峰。\n\n### 没有 mcp-neo4j 时\n- 数据分析师必须手动编写复杂的 Cypher 查询语句来提取“高频购买商品”关系，容易因语法错误导致反复调试。\n- 跨会话的知识（如上次分析的结论）无法自动保留，每次新对话都需重新向 AI 描述业务背景和数据结构。\n- 运维人员需登录 Neo4j Aura 控制台手动创建或扩容实例，流程繁琐且无法在聊天窗口中即时响应突发需求。\n- 验证数据模型是否正确时，需在 Arrows.app 和数据库之间来回切换，缺乏实时的可视化反馈机制。\n\n### 使用 mcp-neo4j 后\n- 分析师直接用自然语言提问“按销量渲染顶部商品图表”，mcp-neo4j-cypher 自动获取 schema 并生成执行准确的查询代码。\n- 借助 mcp-neo4j-memory，AI 能记住“用户 A 偏好电子产品”等实体关系，在不同会话中持续利用已存储的图谱知识进行推理。\n- 通过 mcp-neo4j-cloud-aura-api，用户在对话框中指令“为促销创建 4GB 专业版实例”，系统即刻调用 API 完成实例创建与配置。\n- 利用 mcp-neo4j-data-modeling，团队可在聊天界面直接导入并验证数据模型，实时查看节点与关系的可视化效果，无需切换工具。\n\nmcp-neo4j 将自然语言交互深度融入图数据库管理全流程，让数据查询、记忆持久化、云资源调控及模型验证变得像日常对话一样简单高效。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fneo4j-contrib_mcp-neo4j_b54b67a1.png","neo4j-contrib","Neo4j Contrib","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fneo4j-contrib_65c4fb23.jpg","Public, Open Source Contributions to the Neo4j Ecosystem: Tools, Drivers, Documentation, Visualization",null,"http:\u002F\u002Fneo4j.com\u002Fdeveloper","https:\u002F\u002Fgithub.com\u002Fneo4j-contrib",[85,89,93,97],{"name":86,"color":87,"percentage":88},"Python","#3572A5",99.2,{"name":90,"color":91,"percentage":92},"Dockerfile","#384d54",0.5,{"name":94,"color":95,"percentage":96},"Makefile","#427819",0.3,{"name":98,"color":99,"percentage":100},"Shell","#89e051",0.1,931,241,"2026-04-03T00:56:59","MIT",4,"未说明","不需要 GPU",{"notes":109,"python":106,"dependencies":110},"该工具是连接大语言模型与 Neo4j 的中间件服务器，本身不运行 AI 模型，因此无 GPU 需求。核心依赖是已安装并运行的 Neo4j 数据库实例；其中 'mcp-neo4j-cypher' 服务强制要求 Neo4j 实例安装并启用 APOC 插件以进行模式检查。支持 STDIO、SSE 和 HTTP 多种传输模式，并提供适用于 AWS ECS Fargate 和 Azure Container Apps 的容器化部署方案。",[111,112],"Neo4j 数据库实例","APOC 插件 (针对 mcp-neo4j-cypher)",[14],[115,116,117,118,119],"database","mcp","mcp-server","neo4j","stdio","2026-03-27T02:49:30.150509","2026-04-06T10:26:32.508342",[123,128,133,138,143,148],{"id":124,"question_zh":125,"answer_zh":126,"source_url":127},10592,"如何在 Docker Compose 中将 mcp-neo4j-server 连接到 Neo4j 数据库容器？","该问题已在最新版本中修复。请查阅 Cypher MCP 的 README 文档以获取如何使用 Docker Hub 上的 Cypher MCP 服务器的详细说明。确保在 docker-compose.yml 中正确配置了网络别名和环境变量（如 NEO4J_URL），并确认两个服务位于同一自定义网络中。","https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fissues\u002F48",{"id":129,"question_zh":130,"answer_zh":131,"source_url":132},10593,"在 VS Code Copilot 中使用 read_neo4j_cypher 工具时报错 'TypeError: Cannot use in operator to search for type in true' 怎么办？","这是一个已知兼容性问题。多位用户确认，切换到 VS Code Insiders 版本后错误消失，MCP 服务器可正常工作。此外，该错误通常由 LLM 生成的 Cypher 查询引起，而非 MCP 本身的问题；get_schema 工具因使用预定义查询则不受影响。建议升级至 VS Code Insiders 或检查生成的 Cypher 语句格式。","https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fissues\u002F26",{"id":134,"question_zh":135,"answer_zh":136,"source_url":137},10594,"在 Windows 上运行 MCP Neo4j 服务器连接 Claude 时出现 'coroutine main was never awaited' 警告如何解决？","在 Windows 环境下，需修改入口脚本中的主函数调用方式。将原来的：\nif __name__ == \"__main__\":\n    main()\n替换为：\nif __name__ == \"__main__\":\n    loop = asyncio.get_event_loop()\n    loop.run_until_complete(main())\n此改动能正确启动异步主函数，解决 Claude 无法连接的问题。目前这是在 Windows 上唯一验证有效的解决方案。","https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fissues\u002F93",{"id":139,"question_zh":140,"answer_zh":141,"source_url":142},10595,"为什么 get_neo4j_schema 工具返回的模式信息中缺少关系（relationships）的属性？","早期版本确实存在此限制。维护者已通过 PR #78 修复该问题，修改了底层查询以调用 apoc.graph.meta() 并清理输出，现在 schema 工具会包含关系的属性信息。请确保使用最新版本的 mcp-neo4j-cypher 服务器（已合并到 main 分支），以获得完整的图模式描述，包括节点和关系的属性。","https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fissues\u002F75",{"id":144,"question_zh":145,"answer_zh":146,"source_url":147},10596,"在 Docker 中运行 mcp-neo4j-cypher 时出现 'ValueError: a coroutine was expected, got None' 错误怎么办？","该问题已在后续版本中修复。错误源于异步主函数未被正确调用。请拉取最新的 mcp\u002Fneo4j-cypher Docker 镜像，并参考官方 README 中的部署指南重新配置 docker-compose.yml。确保环境变量（如 NEO4J_URI、NEO4J_USERNAME、NEO4J_PASSWORD）设置正确，且 Neo4j 服务先于 MCP 服务启动完成。","https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fissues\u002F42",{"id":149,"question_zh":150,"answer_zh":151,"source_url":127},10597,"mcp-neo4j-memory 服务器在 Gemini CLI 中有时无法启动是什么原因？","据观察，约三分之一的情况下 mcp-neo4j-memory 服务器在 Gemini CLI 中无法启动，主要与环境变量处理不当有关，导致工具回退到 localhost 连接而失败。建议检查环境变量是否正确传递，并参考 Issue #119 获取更多关于环境配置的细节。同时推荐使用更稳定的 mcp-neo4j-cypher 服务器替代。",[153,158,163,168,173,178,183,188,193,198,203,208,213,218,223,228,233,238,243,248],{"id":154,"version":155,"summary_zh":156,"released_at":157},71169,"mcp-gemini-ext-v1.0.1","## What's Changed\r\n* chore: use extension settings for Gemini CLI extension by @jackwotherspoon in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F278\r\n\r\n## New Contributors\r\n* @jackwotherspoon made their first contribution in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F278\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fcompare\u002Fmcp-neo4j-aura-manager-v0.4.8...mcp-gemini-ext-v1.0.1","2026-03-18T13:36:06",{"id":159,"version":160,"summary_zh":161,"released_at":162},71170,"mcp-neo4j-memory-v0.4.5","### Changed\r\n* Security upgrade python from 3.11-slim to 3.13.8-slim\r\n* Change default MCP server endpoint from \u002Fapi\u002Fmcp\u002F to \u002Fmcp\u002F\r\n* Lock FastMCP version to \u003C3.x\r\n\r\n## New Contributors\r\n* @bryankthompson made their first contribution in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F262\r\n* @AndyHeap-NeoTech made their first contribution in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F200\r\n* @robsdedude made their first contribution in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F203\r\n* @Amitk003 made their first contribution in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F266\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fcompare\u002Fmcp-neo4j-data-modeling-v0.8.2...mcp-neo4j-memory-v0.4.5","2026-02-23T17:30:19",{"id":164,"version":165,"summary_zh":166,"released_at":167},71171,"mcp-neo4j-cypher-v0.5.3","### Changed\r\n* Security upgrade python from 3.12-slim to 3.13.8-slim\r\n* Update default MCP server endpoint from \u002Fapi\u002Fmcp\u002F to \u002Fmcp\u002F\r\n* Lock FastMCP version to \u003C3.x\r\n\r\n## New Contributors\r\n* @bryankthompson made their first contribution in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F262\r\n* @AndyHeap-NeoTech made their first contribution in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F200\r\n* @robsdedude made their first contribution in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F203\r\n* @Amitk003 made their first contribution in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F266\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fcompare\u002Fmcp-neo4j-data-modeling-v0.8.2...mcp-neo4j-cypher-v0.5.3","2026-02-23T17:28:01",{"id":169,"version":170,"summary_zh":171,"released_at":172},71172,"mcp-neo4j-aura-manager-v0.4.8","### Changed\r\n* Docker security upgrade python from 3.11-slim to 3.13.8-slim\r\n* Lock FastMCP version to \u003C3.x\r\n\r\n## New Contributors\r\n* @bryankthompson made their first contribution in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F262\r\n* @AndyHeap-NeoTech made their first contribution in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F200\r\n* @robsdedude made their first contribution in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F203\r\n* @Amitk003 made their first contribution in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F266\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fcompare\u002Fmcp-neo4j-data-modeling-v0.8.2...mcp-neo4j-aura-manager-v0.4.8","2026-02-23T17:29:10",{"id":174,"version":175,"summary_zh":176,"released_at":177},71173,"mcp-neo4j-data-modeling-v0.8.2","### Fixed\r\n* Fixed bug in f-string formatting with Pydantic model export in Python v \u003C 3.12\r\n* Fixed bug in the data modeling Github action that didn't actually test different Python versions due to not specifying the version when executing uv commands.\r\n* Fix Github action to install dev dependencies correctly with uv sync\r\n\r\n### Changed\r\n* Update `pyproject.toml` to declare dev dependencies correctly (previously using deprecated method)\r\n\r\n## What's Changed\r\n* Update data modeling server.json by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F257\r\n* all - bump mcp registry schema versions to 2025-12-11 by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F258\r\n* data modeling - fix f-string bug and github actions bug by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F260\r\n* data modeling - prep v0.8.2 by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F261\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fcompare\u002Fmcp-neo4j-data-modeling-v0.8.1...mcp-neo4j-data-modeling-v0.8.2","2025-12-22T14:52:44",{"id":179,"version":180,"summary_zh":181,"released_at":182},71174,"mcp-neo4j-data-modeling-v0.8.1","### Fixed\r\n* Shorten tool name `export_to_neo4j_python_graphrag_package_schema` to `export_to_neo4j_graphrag_pkg_schema` to be under 60 characters including the default server name.\r\n* Shorten tool name `load_from_neo4j_python_graphrag_package_schema` to `load_from_neo4j_graphrag_pkg_schema` to be under 60 characters including the default server name.\r\n\r\n### Added\r\n* Update README to include new tools and optional `return_validated` argument to validation tools\r\n\r\n## What's Changed\r\n* data modeling - short tool names  by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F251\r\n* data modeling - update readme by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F252\r\n* Update README.md with Official Neo4j MCP Info by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F253\r\n* data modeling - prep v0.8.1 by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F254\r\n* cypher and data modeling - update workflows to execute serially by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F255\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fcompare\u002Fmcp-neo4j-data-modeling-v0.8.0...mcp-neo4j-data-modeling-v0.8.1","2025-12-16T19:56:47",{"id":184,"version":185,"summary_zh":186,"released_at":187},71175,"mcp-neo4j-memory-v0.4.4","## Fixed\r\n* Removed `dependencies=...` from server constructor. This was removed from FastMCP.\r\n\r\n## What's Changed\r\n* update memory server by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F246\r\n* memory - prep v0.4.4 by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F247\r\n* aura manager - prep v0.4.7 by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F248\r\n* cypher - prep v0.5.2 by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F249\r\n* data modeling - prep v0.8.0 by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F250\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fcompare\u002Fmcp-neo4j-memory-v0.4.3...mcp-neo4j-memory-v0.4.4","2025-12-15T19:19:41",{"id":189,"version":190,"summary_zh":191,"released_at":192},71176,"mcp-neo4j-data-modeling-v0.8.0","## v0.8.0\r\n\r\n### Fixed\r\n* Remove `stateless_http` flag on MCP server constructor and move to the appropriate `run_...` function for http and sse transport. The constructor flag is deprecated by FastMCP.\r\n* Removed `dependencies=...` from server constructor. This was removed from FastMCP.\r\n\r\n### Changed\r\n* Make node corners rounded for Mermaid visualization\r\n\r\n### Added\r\n* Add methods to export schema as string representations of Pydantic models for `Node`, `Relationship` and `DataModel`\r\n* Add tool that exports data model as a string representation of a Python file containing imports and Pydantic models\r\n* Add methods to import and export as Neo4j GraphRAG Python Package schema JSON for `Node`, `Relationship` and `DataModel`\r\n* Add tools that import and export data model as Neo4j GraphRAG Python Package schema JSON\r\n* Add `description` field to `Node` and `Relationship` classes\r\n* Add docstring to generated Pydantic nodes and relationships based on `description` field\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fcompare\u002Fmcp-neo4j-aura-manager-v0.4.7...mcp-neo4j-data-modeling-v0.8.0","2025-12-15T19:34:52",{"id":194,"version":195,"summary_zh":196,"released_at":197},71177,"mcp-neo4j-cypher-v0.5.2","### Fixed\r\n* Fix bug in Dockerfile where build would fail due to `LABEL` statement coming before `FROM` statement\r\n* Removed `dependencies=...` from server constructor. This was removed from FastMCP.\r\n\r\n## What's Changed\r\n* cypher - prep v0.5.2 by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F249\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fcompare\u002Fmcp-neo4j-memory-v0.4.3...mcp-neo4j-cypher-v0.5.2","2025-12-15T19:27:19",{"id":199,"version":200,"summary_zh":201,"released_at":202},71178,"mcp-neo4j-aura-manager-v0.4.7","### Fixed\r\n* Removed `dependencies=...` from server constructor. This was removed from FastMCP.\r\n\r\n## What's Changed\r\n* aura manager - prep v0.4.7 by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F248\r\n\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fcompare\u002Fmcp-neo4j-memory-v0.4.3...mcp-neo4j-aura-manager-v0.4.7","2025-12-15T19:23:26",{"id":204,"version":205,"summary_zh":206,"released_at":207},71179,"mcp-neo4j-memory-v0.4.3","### Fixed\r\n* Fix bug in Dockerfile where build would fail due to `LABEL` statement coming before `FROM` statement\r\n\r\n### Changed\r\n* Updated `Entity.type` and `Relation.relationType` Pydantic model fields to have regex checks.\r\n\r\n## What's Changed\r\n* memory - add regex checks to Entity and Relation fields by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F238\r\n* memory - prep v0.4.3 by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F243\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fcompare\u002Fmcp-neo4j-data-modeling-v0.7.0...mcp-neo4j-memory-v0.4.3","2025-12-11T16:58:47",{"id":209,"version":210,"summary_zh":211,"released_at":212},71180,"mcp-neo4j-data-modeling-v0.7.0","### Fixed\r\n* Fix bug in Dockerfile where build would fail due to `LABEL` statement coming before `FROM` statement\r\n\r\n### Changed\r\n* Tools that received Pydantic objects as arguments now also accept JSON strings as input. This is for client applications that send JSON strings instead of objects for tool arguments. This is a workaround for client applications that don't adhere to the defined tool schemas and will be removed in the future once it is not needed.\r\n\r\n### Added\r\n* Added JSON string parsing utils function. This is for client applications that send JSON strings instead of objects for tool arguments. This is a workaround for client applications that don't adhere to the defined tool schemas and will be removed in the future once it is not needed.\r\n\r\n\r\n## What's Changed\r\n* All  - patch dockerfiles by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F230\r\n* Data modeling - allow JSON object and String as tool input by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F231\r\n* Data modeling prep v0.7.0 by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F232\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fcompare\u002Fmcp-neo4j-aura-manager-v0.4.6...mcp-neo4j-data-modeling-v0.7.0","2025-11-19T14:19:03",{"id":214,"version":215,"summary_zh":216,"released_at":217},71181,"mcp-neo4j-aura-manager-v0.4.6","### Fixed\r\n* Fix bug in Dockerfile where build would fail due to `LABEL` statement coming before `FROM` statement\r\n\r\n### Added\r\n* Add `NEO4J_MCP_SERVER_STATELESS` environment variable and `--stateless` cli flag to configure stateless http deployment options when using http or sse transport\r\n\r\n## What's Changed\r\n* aura manager - add stateless flag by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F227\r\n* aura manager - prep v0.4.6 by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F228\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fcompare\u002Fmcp-neo4j-memory-v0.4.2...mcp-neo4j-aura-manager-v0.4.6","2025-11-12T15:10:03",{"id":219,"version":220,"summary_zh":221,"released_at":222},71182,"mcp-neo4j-memory-v0.4.2","## What's Changed\r\n* Memory - add mcp registry config by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F225\r\n* memory - prep v0.4.2 by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F226\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fcompare\u002Fmcp-neo4j-aura-manager-v0.4.5...mcp-neo4j-memory-v0.4.2","2025-11-07T19:54:03",{"id":224,"version":225,"summary_zh":226,"released_at":227},71183,"mcp-neo4j-data-modeling-v0.6.1","## What's Changed\r\n* data modeling - add to github registry by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F214\r\n* Data modeling add to GitHub registry - fix by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F215\r\n* Data modeling add to GitHub registry by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F216\r\n* Data modeling add to GitHub registry by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F217\r\n* data modeling - prep v0.6.1 by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F218\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fcompare\u002Fmcp-neo4j-data-modeling-v0.6.0...mcp-neo4j-data-modeling-v0.6.1","2025-11-07T16:56:33",{"id":229,"version":230,"summary_zh":231,"released_at":232},71184,"mcp-neo4j-cypher-v0.5.1","## What's Changed\r\n* cypher - add mcp registry config by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F219\r\n* cypher - prep v0.5.1 by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F220\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fcompare\u002Fmcp-neo4j-data-modeling-v0.6.1...mcp-neo4j-cypher-v0.5.1","2025-11-07T17:26:38",{"id":234,"version":235,"summary_zh":236,"released_at":237},71185,"mcp-neo4j-aura-manager-v0.4.5","## What's Changed\r\n* aura manager - patch mcp registry config by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F223\r\n* aura manager - prep v0.4.5 by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F224\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fcompare\u002Fmcp-neo4j-aura-manager-v0.4.4...mcp-neo4j-aura-manager-v0.4.5","2025-11-07T18:56:11",{"id":239,"version":240,"summary_zh":241,"released_at":242},71186,"mcp-neo4j-aura-manager-v0.4.4","## What's Changed\r\n* aura manager - add config to deploy to mcp registry by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F221\r\n* aura manager - prep v0.4.4 by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F222\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fcompare\u002Fmcp-neo4j-cypher-v0.5.1...mcp-neo4j-aura-manager-v0.4.4","2025-11-07T18:44:03",{"id":244,"version":245,"summary_zh":246,"released_at":247},71187,"mcp-neo4j-data-modeling-v0.6.0","### Added\r\n* Add import and export methods to `DataModel` for turtle OWL strings\r\n* Add MCP tools for loading and exporting turtle OWL files\r\n\r\n## What's Changed\r\n* data modeling - add turtle owl import \u002F export tools by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F210\r\n* data modeling - prep v0.6.0 by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F213\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fcompare\u002Fmcp-neo4j-cypher-v0.5.0...mcp-neo4j-data-modeling-v0.6.0","2025-11-03T16:47:42",{"id":249,"version":250,"summary_zh":251,"released_at":252},71188,"mcp-neo4j-cypher-v0.5.0","### Added\r\n* Add `NEO4J_SCHEMA_SAMPLE_SIZE` env variable and `schema-sample-size` cli argument to configure the `get_neo4j_schema` sample size\r\n* Update write query detection to include `INSERT` in regex check\r\n\r\n## What's Changed\r\n* Fix write query detection to recognise `INSERT`. by @michael-simons in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F205\r\n* Adding a NEO4J_SAMPLE parameter to enable control of apoc.meta.schema sample size  by @mimomenome in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F211\r\n* cypher - prep v0.5.0 by @a-s-g93 in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F212\r\n\r\n## New Contributors\r\n* @pedroleitao-neo4j made their first contribution in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F198\r\n* @michael-simons made their first contribution in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F205\r\n* @mimomenome made their first contribution in https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fpull\u002F211\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fneo4j-contrib\u002Fmcp-neo4j\u002Fcompare\u002Fmcp-neo4j-aura-manager-v0.4.3...mcp-neo4j-cypher-v0.5.0","2025-11-03T14:23:07"]