[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tool-GoogleCloudPlatform--cloud-run-mcp":3,"similar-GoogleCloudPlatform--cloud-run-mcp":144},{"id":4,"github_repo":5,"name":6,"description_en":7,"description_zh":8,"ai_summary_zh":8,"readme_en":9,"readme_zh":10,"quickstart_zh":11,"use_case_zh":12,"hero_image_url":13,"owner_login":14,"owner_name":15,"owner_avatar_url":16,"owner_bio":17,"owner_company":18,"owner_location":18,"owner_email":18,"owner_twitter":18,"owner_website":19,"owner_url":20,"languages":21,"stars":42,"forks":43,"last_commit_at":44,"license":45,"difficulty_score":46,"env_os":47,"env_gpu":47,"env_ram":47,"env_deps":48,"category_tags":55,"github_topics":58,"view_count":46,"oss_zip_url":18,"oss_zip_packed_at":18,"status":63,"created_at":64,"updated_at":65,"faqs":66,"releases":96},1018,"GoogleCloudPlatform\u002Fcloud-run-mcp","cloud-run-mcp","MCP server to deploy apps to Cloud Run","cloud-run-mcp 是一个开源的 MCP 服务器，它让 AI 助手能够直接部署应用到 Google Cloud Run。通过标准化协议，它将 Claude、Gemini 等 AI 助手与云端部署连接起来，开发者只需用自然语言说\"部署这个应用到云端\"，AI 就能自动完成打包、上传和发布。\n\n它解决了传统部署流程中繁琐的命令操作和上下文切换问题。开发者无需离开对话界面或 IDE，就能完成应用部署、查看服务状态、获取日志等操作，大幅提升开发效率。\n\n这个工具主要面向使用 Google Cloud Run 的开发者，特别是那些已经在使用 AI 助手进行编程、希望进一步实现部署自动化的团队。它也适合构建 AI 驱动的开发工具链的技术负责人。\n\ncloud-run-mcp 的独特之处在于其广泛的集成能力，支持 Gemini CLI、Cursor 等 AI 驱动的 IDE，以及各类基于 Agent SDK 的应用。它提供了一套完整的工具集，既能部署本地文件夹，也能直接部署文件内容，还能管理 GCP 项目，让 AI 真正具备端到端的交付能力。","# Cloud Run MCP server and Gemini CLI extension\n\nEnable MCP-compatible AI agents to deploy apps to Cloud Run.\n\n```json\n\"mcpServers\":{\n  \"cloud-run\": {\n    \"command\": \"npx\",\n    \"args\": [\"-y\", \"@google-cloud\u002Fcloud-run-mcp\"]\n  }\n}\n```\n\nDeploy from Gemini CLI and other AI-powered CLI agents:\n\n\u003Cimg  src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FGoogleCloudPlatform_cloud-run-mcp_readme_8c90c4a29379.gif\" width=\"800\">\n\nDeploy from AI-powered IDEs:\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FGoogleCloudPlatform_cloud-run-mcp_readme_f3804015802b.gif\" width=\"800\">\n\nDeploy from AI assistant apps:\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FGoogleCloudPlatform_cloud-run-mcp_readme_0a879ce26564.gif\" width=\"800\">\n\nDeploy from agent SDKs, like the [Google Gen AI SDK](https:\u002F\u002Fai.google.dev\u002Fgemini-api\u002Fdocs\u002Ffunction-calling?example=meeting#use_model_context_protocol_mcp) or [Agent Development Kit](https:\u002F\u002Fgoogle.github.io\u002Fadk-docs\u002Ftools\u002Fmcp-tools\u002F).\n\n> [!NOTE]  \n> This is the repository of an MCP server to deploy code to Cloud Run, to learn how to **host** MCP servers on Cloud Run, [visit the Cloud Run documentation](https:\u002F\u002Fcloud.google.com\u002Frun\u002Fdocs\u002Fhost-mcp-servers).\n\n## Tools\n\n- `deploy-file-contents`: Deploys files to Cloud Run by providing their contents directly.\n- `list-services`: Lists Cloud Run services in a given project and region.\n- `get-service`: Gets details for a specific Cloud Run service.\n- `get-service-log`: Gets Logs and Error Messages for a specific Cloud Run service.\n\n- `deploy-local-folder`\\*: Deploys a local folder to a Google Cloud Run service.\n- `list-projects`\\*: Lists available GCP projects.\n- `create-project`\\*: Creates a new GCP project and attach it to the first available billing account. A project ID can be optionally specified.\n\n_\\* only available when running locally_\n\n## Prompts\n\nPrompts are natural language commands that can be used to perform common tasks. They are shortcuts for executing tool calls with pre-filled arguments.\n\n- `deploy`: Deploys the current working directory to Cloud Run. If a service name is not provided, it will use the `DEFAULT_SERVICE_NAME` environment variable, or the name of the current working directory.\n- `logs`: Gets the logs for a Cloud Run service. If a service name is not provided, it will use the `DEFAULT_SERVICE_NAME` environment variable, or the name of the current working directory.\n\n## Environment Variables\n\nThe Cloud Run MCP server can be configured using the following environment variables:\n\n| Variable                 | Description                                                                                                                                                                              |\n| :----------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `GOOGLE_CLOUD_PROJECT`   | The default project ID to use for Cloud Run services.                                                                                                                                    |\n| `GOOGLE_CLOUD_REGION`    | The default region to use for Cloud Run services.                                                                                                                                        |\n| `DEFAULT_SERVICE_NAME`   | The default service name to use for Cloud Run services.                                                                                                                                  |\n| `SKIP_IAM_CHECK`         | Controls whether to check for IAM permissions for a Cloud Run service. Set to `false` to enable checks. This is `true` by default which is a recommended way to make the service public. |\n| `ENABLE_HOST_VALIDATION` | Prevents [DNS Rebinding](https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FDNS_rebinding) attacks by validating the Host header. This is disabled by default.                                                |\n| `ALLOWED_HOSTS`          | Comma-separated list of allowed Host headers (if host validation is enabled). The default value is `localhost,127.0.0.1,::1`.                                                            |\n\n## Use as a Gemini CLI extension\n\nTo install this as a [Gemini CLI](https:\u002F\u002Fgithub.com\u002Fgoogle-gemini\u002Fgemini-cli) extension, run the following command:\n\n2. Install the extension:\n\n   ```bash\n   gemini extensions install https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\n   ```\n\n3. Log in to your Google Cloud account using the command:\n\n   ```bash\n   gcloud auth login\n   ```\n\n4. Set up application credentials using the command:\n   ```bash\n   gcloud auth application-default login\n   ```\n\n## Use in MCP Clients\n\n### Learn how to configure your MCP client\n\nMost MCP clients require a configuration file to be created or modified to add the MCP server.\n\nThe configuration file syntax can be different across clients. Please refer to the following links for the latest expected syntax:\n\n- [**Antigravity**](https:\u002F\u002Fantigravity.google\u002Fdocs\u002Fmcp)\n- [**Windsurf**](https:\u002F\u002Fdocs.windsurf.com\u002Fwindsurf\u002Fmcp)\n- [**VSCode**](https:\u002F\u002Fcode.visualstudio.com\u002Fdocs\u002Fcopilot\u002Fchat\u002Fmcp-servers)\n- [**Claude Desktop**](https:\u002F\u002Fmodelcontextprotocol.io\u002Fquickstart\u002Fuser)\n- [**Cursor**](https:\u002F\u002Fdocs.cursor.com\u002Fcontext\u002Fmodel-context-protocol)\n\nOnce you have identified how to configure your MCP client, select one of these two options to set up the MCP server.\nWe recommend setting up as a local MCP server using Node.js.\n\n### Set up as local MCP server\n\nRun the Cloud Run MCP server on your local machine using local Google Cloud credentials. This is best if you are using an AI-assisted IDE (e.g. Cursor) or a desktop AI application (e.g. Claude).\n\n1. Install the [Google Cloud SDK](https:\u002F\u002Fcloud.google.com\u002Fsdk\u002Fdocs\u002Finstall) and authenticate with your Google account.\n\n2. Log in to your Google Cloud account using the command:\n\n   ```bash\n   gcloud auth login\n   ```\n\n3. Set up application credentials using the command:\n   ```bash\n   gcloud auth application-default login\n   ```\n\nThen configure the MCP server using either Node.js or Docker:\n\n#### Using Node.js\n\n0. Install [Node.js](https:\u002F\u002Fnodejs.org\u002Fen\u002Fdownload\u002F) (LTS version recommended).\n\n1. Update the MCP configuration file of your MCP client with the following:\n\n   ```json\n      \"cloud-run\": {\n        \"command\": \"npx\",\n        \"args\": [\"-y\", \"@google-cloud\u002Fcloud-run-mcp\"]\n      }\n   ```\n\n2. [Optional] Add default configurations\n\n   ```json\n      \"cloud-run\": {\n         \"command\": \"npx\",\n         \"args\": [\"-y\", \"@google-cloud\u002Fcloud-run-mcp\"],\n         \"env\": {\n               \"GOOGLE_CLOUD_PROJECT\": \"PROJECT_NAME\",\n               \"GOOGLE_CLOUD_REGION\": \"PROJECT_REGION\",\n               \"DEFAULT_SERVICE_NAME\": \"SERVICE_NAME\"\n         }\n      }\n   ```\n\n#### Using Docker\n\nSee Docker's [MCP catalog](https:\u002F\u002Fhub.docker.com\u002Fmcp\u002Fserver\u002Fcloud-run-mcp\u002Foverview), or use these manual instructions:\n\n0. Install [Docker](https:\u002F\u002Fwww.docker.com\u002Fget-started\u002F)\n\n1. Update the MCP configuration file of your MCP client with the following:\n\n   ```json\n      \"cloud-run\": {\n        \"command\": \"docker\",\n        \"args\": [\n          \"run\",\n          \"-i\",\n          \"--rm\",\n          \"-e\",\n          \"GOOGLE_APPLICATION_CREDENTIALS\",\n          \"-v\",\n          \"\u002Flocal-directory:\u002Flocal-directory\",\n          \"mcp\u002Fcloud-run-mcp:latest\"\n        ],\n        \"env\": {\n          \"GOOGLE_APPLICATION_CREDENTIALS\": \"\u002FUsers\u002Fslim\u002F.config\u002Fgcloud\u002Fapplication_default-credentials.json\",\n          \"DEFAULT_SERVICE_NAME\": \"SERVICE_NAME\"\n        }\n      }\n   ```\n\n### Set up as remote MCP server\n\n> [!WARNING]  \n> Do not use the remote MCP server without authentication. In the following instructions, we will use IAM authentication to secure the connection to the MCP server from your local machine. This is important to prevent unauthorized access to your Google Cloud resources.\n\nRun the Cloud Run MCP server itself on Cloud Run with connection from your local machine authenticated via IAM.\nWith this option, you will only be able to deploy code to the same Google Cloud project as where the MCP server is running.\n\n1. Install the [Google Cloud SDK](https:\u002F\u002Fcloud.google.com\u002Fsdk\u002Fdocs\u002Finstall) and authenticate with your Google account.\n\n2. Log in to your Google Cloud account using the command:\n\n   ```bash\n   gcloud auth login\n   ```\n\n3. Set your Google Cloud project ID using the command:\n   ```bash\n   gcloud config set project YOUR_PROJECT_ID\n   ```\n4. Deploy the Cloud Run MCP server to Cloud Run:\n\n   ```bash\n   gcloud run deploy cloud-run-mcp --image us-docker.pkg.dev\u002Fcloudrun\u002Fcontainer\u002Fmcp --no-allow-unauthenticated\n   ```\n\n   When prompted, pick a region, for example `europe-west1`.\n\n   Note that the MCP server is _not_ publicly accessible, it requires authentication via IAM.\n\n5. [Optional] Add default configurations\n\n   ```bash\n   gcloud run services update cloud-run-mcp --region=REGION --update-env-vars GOOGLE_CLOUD_PROJECT=PROJECT_NAME,GOOGLE_CLOUD_REGION=PROJECT_REGION,DEFAULT_SERVICE_NAME=SERVICE_NAME,SKIP_IAM_CHECK=false\n   ```\n\n6. Run a Cloud Run proxy on your local machine to connect securely using your identity to the remote MCP server running on Cloud Run:\n\n   ```bash\n   gcloud run services proxy cloud-run-mcp --port=3000 --region=REGION --project=PROJECT_ID\n   ```\n\n   This will create a local proxy on port 3000 that forwards requests to the remote MCP server and injects your identity.\n\n7. Update the MCP configuration file of your MCP client with the following:\n\n   ```json\n      \"cloud-run\": {\n        \"url\": \"http:\u002F\u002Flocalhost:3000\u002Fsse\"\n      }\n\n   ```\n\n   If your MCP client does not support the `url` attribute, you can use [mcp-remote](https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Fmcp-remote):\n\n   ```json\n      \"cloud-run\": {\n        \"command\": \"npx\",\n        \"args\": [\"-y\", \"mcp-remote\", \"http:\u002F\u002Flocalhost:3000\u002Fsse\"]\n      }\n   ```\n\n## Using MCP Server with OAuth\n\nCloud Run MCP server supports OAuth as an authentication mechanism. In order to use OAuth, create the OAuth client, and configure a `.env` file with the appropriate values pertaining to your OAuth client. A `.env.example` is provided for reference.\n\nThe Cloud Run MCP server works seamlessly with Google Cloud SDK OAuth client. In order to leverage the Google Cloud SDK OAuth client, you can use the `.env.gcloud-sdk-oauth` file as your `.env` file as follows:\n\n```bash\ncp .env.gcloud-sdk-oauth .env\nnode mcp-server.js\n```\n\n### Configure MCP Server on Gemini CLI to use OAuth\n\nWhen the Cloud Run MCP server is started in the OAuth mode, the MCP client should also be configured to use OAuth. You can setup the MCP server in OAuth mode in the Gemini CLI by using the following JSON in the `~\u002F.gemini\u002Fsettings.json` file:\n\n```json\n{\n  \"mcpServers\": {\n    \"cloud-run\": {\n      \"httpUrl\": \"http:\u002F\u002Flocalhost:3000\u002Fmcp\",\n      \"oauth\": {\n        \"enabled\": true,\n        \"clientId\": \"\u003COAUTH_CLIENT_ID>\",\n        \"clientSecret\": \"\u003COAUTH_CLIENT_SECRET>\"\n      }\n    }\n  }\n}\n```\n\nPost the configuration changes as shown above, start the Gemini CLI. You should authenticate the Cloud Run MCP server using the following prompt in the Gemini CLI:\n\n```\n\u002Fmcp auth cloud-run\n```\n\nThis will take you to the authentication page on your browser, wherein you need to sign in using the appropriate gmail id, and accept the terms and conditions. Once the authentication is succcessful, you can come back to the Gemini CLI, and the Cloud Run MCP server will be ready to use.\n\nThe Google Cloud Platform Terms of Service (available at https:\u002F\u002Fcloud.google.com\u002Fterms\u002F) and the Data Processing and Security Terms (available at https:\u002F\u002Fcloud.google.com\u002Fterms\u002Fdata-processing-terms) do not apply to any component of the Cloud Run MCP Server software.\n","# Cloud Run MCP 服务器和 Gemini CLI 扩展\n\n使兼容 MCP（模型上下文协议）的人工智能代理能够将应用部署到 Cloud Run。\n\n```json\n\"mcpServers\":{\n  \"cloud-run\": {\n    \"command\": \"npx\",\n    \"args\": [\"-y\", \"@google-cloud\u002Fcloud-run-mcp\"]\n  }\n}\n```\n\n从 Gemini CLI 和其他由 AI 驱动的 CLI 代理部署：\n\n\u003Cimg  src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FGoogleCloudPlatform_cloud-run-mcp_readme_8c90c4a29379.gif\" width=\"800\">\n\n从由 AI 驱动的集成开发环境（IDE）部署：\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FGoogleCloudPlatform_cloud-run-mcp_readme_f3804015802b.gif\" width=\"800\">\n\n从 AI 助手应用部署：\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FGoogleCloudPlatform_cloud-run-mcp_readme_0a879ce26564.gif\" width=\"800\">\n\n从代理软件开发工具包（SDK）部署，例如 [Google Gen AI SDK](https:\u002F\u002Fai.google.dev\u002Fgemini-api\u002Fdocs\u002Ffunction-calling?example=meeting#use_model_context_protocol_mcp) 或 [Agent Development Kit](https:\u002F\u002Fgoogle.github.io\u002Fadk-docs\u002Ftools\u002Fmcp-tools\u002F)。\n\n> [!NOTE]  \n> 本仓库是一个用于将代码部署到 Cloud Run 的 MCP 服务器，要了解如何在 Cloud Run 上**托管**MCP 服务器，请[访问 Cloud Run 文档](https:\u002F\u002Fcloud.google.com\u002Frun\u002Fdocs\u002Fhost-mcp-servers)。\n\n## 工具\n\n- `deploy-file-contents`：通过直接提供文件内容将文件部署到 Cloud Run。\n- `list-services`：列出指定项目和区域中的 Cloud Run 服务。\n- `get-service`：获取特定 Cloud Run 服务的详细信息。\n- `get-service-log`：获取特定 Cloud Run 服务的日志和错误信息。\n\n- `deploy-local-folder`\\*：将本地文件夹部署到 Google Cloud Run 服务。\n- `list-projects`\\*：列出可用的 GCP（Google Cloud Platform）项目。\n- `create-project`\\*：创建一个新的 GCP 项目并将其关联到第一个可用的结算账号。可以选填项目 ID。\n\n_\\* 仅在本地运行时可用_\n\n## 提示词\n\n提示词是可用来执行常见任务的自然语言命令。它们是使用预填充参数执行工具调用的快捷方式。\n\n- `deploy`：将当前工作目录部署到 Cloud Run。如果未提供服务名称，将使用 `DEFAULT_SERVICE_NAME` 环境变量或当前工作目录的名称。\n- `logs`：获取 Cloud Run 服务的日志。如果未提供服务名称，将使用 `DEFAULT_SERVICE_NAME` 环境变量或当前工作目录的名称。\n\n## 环境变量\n\n可以使用以下环境变量配置 Cloud Run MCP 服务器：\n\n| 变量                     | 描述                                                                                                                                                                              |\n| :----------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `GOOGLE_CLOUD_PROJECT`   | 用于 Cloud Run 服务的默认项目 ID。                                                                                                                                    |\n| `GOOGLE_CLOUD_REGION`    | 用于 Cloud Run 服务的默认区域。                                                                                                                                        |\n| `DEFAULT_SERVICE_NAME`   | 用于 Cloud Run 服务的默认服务名称。                                                                                                                                  |\n| `SKIP_IAM_CHECK`         | 控制是否检查 Cloud Run 服务的 IAM（身份和访问管理）权限。设置为 `false` 以启用检查。默认为 `true`，这是将服务公开的建议方式。 |\n| `ENABLE_HOST_VALIDATION` | 通过验证 Host 请求头防止 DNS 重绑定攻击。默认禁用。                                                |\n| `ALLOWED_HOSTS`          | 允许的 Host 请求头的逗号分隔列表（如果启用了主机验证）。默认值为 `localhost,127.0.0.1,::1`。                                                            |\n\n## 用作 Gemini CLI 扩展\n\n要将此工具安装为 [Gemini CLI](https:\u002F\u002Fgithub.com\u002Fgoogle-gemini\u002Fgemini-cli) 扩展，请运行以下命令：\n\n2. 安装扩展：\n\n   ```bash\n   gemini extensions install https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\n   ```\n\n3. 使用以下命令登录您的 Google Cloud 账号：\n\n   ```bash\n   gcloud auth login\n   ```\n\n4. 使用以下命令设置应用凭据：\n   ```bash\n   gcloud auth application-default login\n   ```\n\n## 在 MCP 客户端中使用\n\n### 了解如何配置您的 MCP 客户端\n\n大多数 MCP 客户端需要创建或修改配置文件以添加 MCP 服务器。\n\n不同客户端的配置文件语法可能不同。请参考以下链接获取最新的预期语法：\n\n- [**Antigravity**](https:\u002F\u002Fantigravity.google\u002Fdocs\u002Fmcp)\n- [**Windsurf**](https:\u002F\u002Fdocs.windsurf.com\u002Fwindsurf\u002Fmcp)\n- [**VSCode**](https:\u002F\u002Fcode.visualstudio.com\u002Fdocs\u002Fcopilot\u002Fchat\u002Fmcp-servers)\n- [**Claude Desktop**](https:\u002F\u002Fmodelcontextprotocol.io\u002Fquickstart\u002Fuser)\n- [**Cursor**](https:\u002F\u002Fdocs.cursor.com\u002Fcontext\u002Fmodel-context-protocol)\n\n确定如何配置您的 MCP 客户端后，请选择以下两个选项之一来设置 MCP 服务器。\n我们建议使用 Node.js 将其设置为本地 MCP 服务器。\n\n### 设置为本地 MCP (模型上下文协议) 服务器\n\n使用本地 Google Cloud 凭据在本地机器上运行 Cloud Run MCP 服务器。如果您使用的是 AI 辅助 IDE (集成开发环境)（例如 Cursor）或桌面 AI 应用程序（例如 Claude），这是最佳选择。\n\n1. 安装 [Google Cloud SDK (软件开发工具包)](https:\u002F\u002Fcloud.google.com\u002Fsdk\u002Fdocs\u002Finstall) 并使用您的 Google 账号进行身份验证。\n\n2. 使用以下命令登录您的 Google Cloud 账号：\n\n   ```bash\n   gcloud auth login\n   ```\n\n3. 使用以下命令设置应用凭据：\n   ```bash\n   gcloud auth application-default login\n   ```\n\n然后使用 Node.js 或 Docker 配置 MCP 服务器：\n\n#### 使用 Node.js\n\n0. 安装 [Node.js](https:\u002F\u002Fnodejs.org\u002Fen\u002Fdownload\u002F)（建议使用 LTS 版本）。\n\n1. 使用以下内容更新您的 MCP 客户端的 MCP 配置文件：\n\n   ```json\n      \"cloud-run\": {\n        \"command\": \"npx\",\n        \"args\": [\"-y\", \"@google-cloud\u002Fcloud-run-mcp\"]\n      }\n   ```\n\n2. [可选] 添加默认配置\n\n   ```json\n      \"cloud-run\": {\n         \"command\": \"npx\",\n         \"args\": [\"-y\", \"@google-cloud\u002Fcloud-run-mcp\"],\n         \"env\": {\n               \"GOOGLE_CLOUD_PROJECT\": \"PROJECT_NAME\",\n               \"GOOGLE_CLOUD_REGION\": \"PROJECT_REGION\",\n               \"DEFAULT_SERVICE_NAME\": \"SERVICE_NAME\"\n         }\n      }\n   ```\n\n#### 使用 Docker\n\n请参阅 Docker 的 [MCP 目录](https:\u002F\u002Fhub.docker.com\u002Fmcp\u002Fserver\u002Fcloud-run-mcp\u002Foverview)，或使用以下手动说明：\n\n0. 安装 [Docker](https:\u002F\u002Fwww.docker.com\u002Fget-started\u002F)\n\n1. 使用以下内容更新您的 MCP 客户端的 MCP 配置文件：\n\n   ```json\n      \"cloud-run\": {\n        \"command\": \"docker\",\n        \"args\": [\n          \"run\",\n          \"-i\",\n          \"--rm\",\n          \"-e\",\n          \"GOOGLE_APPLICATION_CREDENTIALS\",\n          \"-v\",\n          \"\u002Flocal-directory:\u002Flocal-directory\",\n          \"mcp\u002Fcloud-run-mcp:latest\"\n        ],\n        \"env\": {\n          \"GOOGLE_APPLICATION_CREDENTIALS\": \"\u002FUsers\u002Fslim\u002F.config\u002Fgcloud\u002Fapplication_default-credentials.json\",\n          \"DEFAULT_SERVICE_NAME\": \"SERVICE_NAME\"\n        }\n      }\n   ```\n\n### 设置为远程 MCP (模型上下文协议) 服务器\n\n> [!警告]  \n> 请勿在没有身份验证的情况下使用远程 MCP 服务器。在以下说明中，我们将使用 IAM (身份和访问管理) 身份验证来保护从本地机器到 MCP 服务器的连接。这对于防止未经授权访问您的 Google Cloud 资源非常重要。\n\n在 Cloud Run 上运行 Cloud Run MCP 服务器本身，并通过 IAM 对来自本地机器的连接进行身份验证。\n使用此选项，您只能将代码部署到与 MCP 服务器运行位置相同的 Google Cloud 项目中。\n\n1. 安装 [Google Cloud SDK (软件开发工具包)](https:\u002F\u002Fcloud.google.com\u002Fsdk\u002Fdocs\u002Finstall) 并使用您的 Google 账号进行身份验证。\n\n2. 使用以下命令登录您的 Google Cloud 账号：\n\n   ```bash\n   gcloud auth login\n   ```\n\n3. 使用以下命令设置您的 Google Cloud 项目 ID：\n   ```bash\n   gcloud config set project YOUR_PROJECT_ID\n   ```\n4. 将 Cloud Run MCP 服务器部署到 Cloud Run：\n\n   ```bash\n   gcloud run deploy cloud-run-mcp --image us-docker.pkg.dev\u002Fcloudrun\u002Fcontainer\u002Fmcp --no-allow-unauthenticated\n   ```\n\n   出现提示时，选择一个区域，例如 `europe-west1`。\n\n   请注意，MCP 服务器_不_可公开访问，它需要通过 IAM 进行身份验证。\n\n5. [可选] 添加默认配置\n\n   ```bash\n   gcloud run services update cloud-run-mcp --region=REGION --update-env-vars GOOGLE_CLOUD_PROJECT=PROJECT_NAME,GOOGLE_CLOUD_REGION=PROJECT_REGION,DEFAULT_SERVICE_NAME=SERVICE_NAME,SKIP_IAM_CHECK=false\n   ```\n\n6. 在本地机器上运行 Cloud Run 代理，以使用您的身份安全地连接到在 Cloud Run 上运行的远程 MCP 服务器：\n\n   ```bash\n   gcloud run services proxy cloud-run-mcp --port=3000 --region=REGION --project=PROJECT_ID\n   ```\n\n   这将在端口 3000 上创建一个本地代理，将请求转发到远程 MCP 服务器并注入您的身份。\n\n7. 使用以下内容更新您的 MCP 客户端的 MCP 配置文件：\n\n   ```json\n      \"cloud-run\": {\n        \"url\": \"http:\u002F\u002Flocalhost:3000\u002Fsse\"\n      }\n\n   ```\n\n   如果您的 MCP 客户端不支持 `url` 属性，您可以使用 [mcp-remote](https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Fmcp-remote)：\n\n   ```json\n      \"cloud-run\": {\n        \"command\": \"npx\",\n        \"args\": [\"-y\", \"mcp-remote\", \"http:\u002F\u002Flocalhost:3000\u002Fsse\"]\n      }\n   ```\n\n## 使用支持 OAuth (开放授权) 的 MCP 服务器\n\nCloud Run MCP 服务器支持 OAuth 作为身份验证机制。为了使用 OAuth，请创建 OAuth 客户端，并使用与您的 OAuth 客户端相关的适当值配置 `.env` 文件。提供了 `.env.example` 作为参考。\n\nCloud Run MCP 服务器可与 Google Cloud SDK OAuth 客户端无缝协作。为了利用 Google Cloud SDK OAuth 客户端，您可以按如下方式将 `.env.gcloud-sdk-oauth` 文件用作您的 `.env` 文件：\n\n```bash\ncp .env.gcloud-sdk-oauth .env\nnode mcp-server.js\n```\n\n### 在 Gemini CLI (命令行界面) 上配置 MCP 服务器以使用 OAuth\n\n当 Cloud Run MCP 服务器以 OAuth 模式启动时，MCP 客户端也应配置为使用 OAuth。您可以通过在 `~\u002F.gemini\u002Fsettings.json` 文件中使用以下 JSON 在 Gemini CLI 中设置 OAuth 模式的 MCP 服务器：\n\n```json\n{\n  \"mcpServers\": {\n    \"cloud-run\": {\n      \"httpUrl\": \"http:\u002F\u002Flocalhost:3000\u002Fmcp\",\n      \"oauth\": {\n        \"enabled\": true,\n        \"clientId\": \"\u003COAUTH_CLIENT_ID>\",\n        \"clientSecret\": \"\u003COAUTH_CLIENT_SECRET>\"\n      }\n    }\n  }\n}\n```\n\n完成上述配置更改后，启动 Gemini CLI。您应该使用 Gemini CLI 中的以下提示对 Cloud Run MCP 服务器进行身份验证：\n\n```\n\u002Fmcp auth cloud-run\n```\n\n这将带您进入浏览器中的身份验证页面，您需要使用适当的 Gmail 账号登录，并接受条款和条件。身份验证成功后，您可以返回 Gemini CLI，Cloud Run MCP 服务器即可使用。\n\nGoogle Cloud Platform 服务条款（可在 https:\u002F\u002Fcloud.google.com\u002Fterms\u002F 获取）和数据处理与安全条款（可在 https:\u002F\u002Fcloud.google.com\u002Fterms\u002Fdata-processing-terms 获取）不适用于 Cloud Run MCP Server 软件的任何组件。","# cloud-run-mcp 快速上手指南\n\n## 环境准备\n\n### 系统要求\n- **Node.js**: LTS 版本（推荐 v20+）\n- **Google Cloud SDK**: 最新版\n- **操作系统**: macOS、Linux 或 Windows\n\n### 前置依赖\n1. 注册 [Google Cloud 账号](https:\u002F\u002Fcloud.google.com\u002F)并创建项目\n2. 安装 Node.js（国内可使用 [淘宝镜像](https:\u002F\u002Fnpmmirror.com\u002F)加速）\n3. 安装 [Google Cloud SDK](https:\u002F\u002Fcloud.google.com\u002Fsdk\u002Fdocs\u002Finstall)\n\n## 安装步骤\n\n### 1. 配置 Google Cloud 认证\n```bash\n# 登录 Google Cloud 账号\ngcloud auth login\n\n# 设置应用默认凭证\ngcloud auth application-default login\n\n# 设置默认项目（可选）\ngcloud config set project YOUR_PROJECT_ID\n```\n\n### 2. 配置 MCP 客户端\n\n在您的 MCP 客户端配置文件中添加以下内容（如 Cursor、Claude Desktop 等）：\n\n```json\n{\n  \"mcpServers\": {\n    \"cloud-run\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@google-cloud\u002Fcloud-run-mcp\"],\n      \"env\": {\n        \"GOOGLE_CLOUD_PROJECT\": \"YOUR_PROJECT_ID\",\n        \"GOOGLE_CLOUD_REGION\": \"us-central1\"\n      }\n    }\n  }\n}\n```\n\n**国内加速方案**：若 npx 下载缓慢，可配置 npm 淘宝镜像：\n```bash\nnpm config set registry https:\u002F\u002Fregistry.npmmirror.com\n```\n\n## 基本使用\n\n### 部署应用\n在 AI 客户端中输入自然语言指令：\n```\n将当前目录部署到 Cloud Run\n```\n\n或使用默认服务名部署：\n```\n使用 cloud-run 部署\n```\n\n### 常用操作\n- **查看服务列表**: \"列出 Cloud Run 服务\"\n- **获取服务详情**: \"获取服务 my-service 的信息\"\n- **查看日志**: \"获取 cloud-run 日志\"\n\n### 环境变量配置\n在 MCP 配置中可设置以下变量：\n\n| 变量名 | 说明 | 示例 |\n|--------|------|------|\n| `GOOGLE_CLOUD_PROJECT` | 默认项目 ID | `my-project-123` |\n| `GOOGLE_CLOUD_REGION` | 默认区域 | `asia-east1` |\n| `DEFAULT_SERVICE_NAME` | 默认服务名 | `my-app` |\n\n### 快速部署示例\n1. 进入项目目录：`cd my-app`\n2. 在 AI 客户端输入：`部署到 Cloud Run`\n3. 工具会自动打包当前目录并部署\n\n**提示**：首次部署可能需要启用 Cloud Run API，按提示操作即可。","全栈开发者李明正在开发一个 AI 图像处理 API 服务，使用 Python + FastAPI 构建，需要频繁部署到 Cloud Run 进行测试和迭代。每次修改算法或接口后，他都要手动执行部署流程，这成为了日常开发中最耗时的环节。\n\n### 没有 cloud-run-mcp 时\n\n- 部署过程繁琐易错：需要反复输入 `gcloud run deploy` 命令，手动指定项目 ID、区域、服务名称等参数，经常因为拼写错误导致部署失败\n- 开发流频繁中断：在 VS Code 中写完代码后，必须切换到终端，回忆并输入复杂命令，上下文切换严重打断编程思路\n- 日志排查效率低：服务启动失败时，需要另外执行 `gcloud logs read` 命令，手动查找错误信息，定位问题耗时超过 15 分钟\n- 无法通过 AI 助手操作：想使用 Gemini CLI 快速部署时，发现它无法直接调用 Cloud Run API，只能返回命令建议，仍需手动执行\n- 多环境管理混乱：同时维护开发、测试两个服务时，经常混淆服务名称和配置，误操作风险高\n\n### 使用 cloud-run-mcp 后\n\n- 自然语言一键部署：在 IDE 中直接对 AI 助手说\"把当前目录部署到 Cloud Run\"，cloud-run-mcp 自动读取环境变量完成部署，无需记忆任何命令\n- 开发流无缝衔接：在 Cursor 或 Windsurf 中修改代码后，直接通过 AI 聊天界面执行部署，整个过程不离开编辑器，保持专注状态\n- 即时获取日志分析：只需询问\"为什么我的服务启动失败了\"，cloud-run-mcp 自动拉取日志并交给 AI 分析，2 分钟内定位到是内存配置不足的问题\n- 深度集成 AI 工作流：通过 Gemini CLI 说出\"部署并检查状态\"，工具自动完成部署、验证服务健康、输出访问地址的完整流程\n- 智能环境管理：利用 `DEFAULT_SERVICE_NAME` 环境变量，AI 自动识别当前分支并部署到对应环境，避免人为配置错误\n\ncloud-run-mcp 将 Cloud Run 部署从重复的手动操作转变为自然语言驱动的智能流程，让开发者能专注于代码本身而非部署细节。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FGoogleCloudPlatform_cloud-run-mcp_8c90c4a2.gif","GoogleCloudPlatform","Google Cloud Platform","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002FGoogleCloudPlatform_85ccccae.png","",null,"https:\u002F\u002Fcloud.google.com","https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform",[22,26,30,34,38],{"name":23,"color":24,"percentage":25},"JavaScript","#f1e05a",98.9,{"name":27,"color":28,"percentage":29},"Dockerfile","#384d54",0.5,{"name":31,"color":32,"percentage":33},"Go","#00ADD8",0.3,{"name":35,"color":36,"percentage":37},"Java","#b07219",0.2,{"name":39,"color":40,"percentage":41},"Python","#3572A5",0.1,584,103,"2026-04-04T20:29:12","Apache-2.0",3,"未说明",{"notes":49,"python":47,"dependencies":50},"该工具是基于 Node.js 的 MCP 服务器，用于将应用部署到 Cloud Run。必须安装 Node.js (推荐LTS版本) 和 Google Cloud SDK，并完成 `gcloud auth login` 和 `gcloud auth application-default login` 认证。支持三种运行方式：1) 本地 Node.js 运行 2) Docker 容器运行 3) 部署到 Cloud Run 作为远程 MCP 服务器。注意：deploy-local-folder、list-projects、create-project 这三个工具仅在本地运行时可用。可通过环境变量配置默认项目ID、区域和服务名称，支持 OAuth 认证模式。",[51,52,53,54],"@google-cloud\u002Fcloud-run-mcp","Node.js (LTS版本)","Google Cloud SDK","gcloud CLI",[56,57],"Agent","插件",[59,60,61,62],"mcp-server","google-cloud","google-cloud-run","mcp","ready","2026-03-27T02:49:30.150509","2026-04-06T05:36:54.831796",[67,72,77,82,87,92],{"id":68,"question_zh":69,"answer_zh":70,"source_url":71},4539,"部署 Cloud Run 服务时提示「IAM API 未启用」错误，但实际已启用怎么办？","此错误通常由 IAM 权限传播延迟导致。解决方案：1) 等待 2-3 分钟后重试部署，通常即可成功；2) 确保本地应用默认凭证(ADC)对目标项目有访问权限；3) 项目已合并 PR #80 改进错误处理。如问题持续，请检查凭证是否配置正确。","https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fissues\u002F52",{"id":73,"question_zh":74,"answer_zh":75,"source_url":76},4540,"在新创建的 GCP 项目中部署时遇到「权限被拒绝」错误如何解决？","新项目的 IAM 权限需要时间传播。请执行：1) 设置项目：`gcloud config set project [PROJECT_ID]`；2) 更新 ADC 凭证：`gcloud auth application-default login`；3) 验证凭证中的项目 ID：`cat ~\u002F.config\u002Fgcloud\u002Fapplication_default_credentials.json | grep quota_project_id`；4) 等待几分钟后重试部署。","https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fissues\u002F74",{"id":78,"question_zh":79,"answer_zh":80,"source_url":81},4541,"使用 Gemini CLI 安装或更新 Cloud Run 扩展失败，提示配置文件找不到怎么办？","此问题通常与 Gemini CLI 的归档提取逻辑有关，而非 MCP 服务器本身。建议：1) 确认使用最新版 Gemini CLI；2) 访问 https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Freleases 查看版本信息；3) 该扩展的 GitHub 发布版本与 npm 包版本一一对应。如问题持续，请向 Gemini CLI 团队反馈。","https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fissues\u002F153",{"id":83,"question_zh":84,"answer_zh":85,"source_url":86},4542,"运行 `npx @google-cloud\u002Fcloud-run-mcp` 时提示「command not found」如何解决？","尝试以下步骤：1) 清理 npm 缓存：`npm cache clean --force`；2) 使用替代命令：`npx -y https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp`；3) 确保 npm 为较新版本。此问题通常由缓存或包解析异常引起。","https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fissues\u002F96",{"id":88,"question_zh":89,"answer_zh":90,"source_url":91},4543,"通过 \u002Fdeploy 部署的服务默认需要身份验证，如何公开访问？","当前版本默认部署为需要身份验证的模式，这是预期的安全行为。如需公开访问，部署后需手动执行：`gcloud run services update [SERVICE] --allow-unauthenticated`，或在 Cloud Console 中修改服务设置。项目计划未来支持直接部署公开服务。","https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fissues\u002F62",{"id":93,"question_zh":94,"answer_zh":95,"source_url":71},4544,"为什么部署时会出现 IAM 权限传播问题，如何避免？","IAM 权限更改在 GCP 中需要 30-90 秒传播时间。为避免部署失败：1) 启用 API 或修改权限后等待 2 分钟再部署；2) 如遇错误，重试通常可解决；3) 对于新项目，确保所有必需 API 已启用且权限已传播。此问题在多个 Issue 中被报告，项目正在改进错误处理逻辑。",[97,102,107,112,117,122,127,132,136,140],{"id":98,"version":99,"summary_zh":100,"released_at":101},103985,"v1.10.0","## What's Changed\r\n* feat: accept projectId and region via gemini settings by @shruti-mantri in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F226\r\n* build(deps): bump minimatch by @dependabot[bot] in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F227\r\n* feat: add universal maker for zip deploy of nodejs and python by @shruti-mantri in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F223\r\n* build(deps): bump hono from 4.12.0 to 4.12.2 by @dependabot[bot] in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F228\r\n* build(deps): bump fast-xml-parser from 5.3.6 to 5.4.1 by @dependabot[bot] in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F229\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fcompare\u002Fv1.9.0...v1.10.0","2026-03-04T14:41:55",{"id":103,"version":104,"summary_zh":105,"released_at":106},103986,"v1.9.0","## What's Changed\r\n* feat: add OAuth related GET urls by @shruti-mantri in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F207\r\n* fix: vulnerability in hono package by @shruti-mantri in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F215\r\n* feat: support oauth by @shruti-mantri in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F214\r\n* build(deps): bump @modelcontextprotocol\u002Fsdk from 1.25.2 to 1.26.0 by @dependabot[bot] in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F216\r\n* build(deps): bump qs from 6.14.1 to 6.14.2 by @dependabot[bot] in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F218\r\n* feat: add instructions to use OAuth by @shruti-mantri in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F219\r\n* build(deps): bump fast-xml-parser and @google-cloud\u002Fstorage by @dependabot[bot] in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F220\r\n* build(deps): bump ajv from 8.17.1 to 8.18.0 by @dependabot[bot] in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F221\r\n* Remove kokoro config from Github repo by @husainhirani in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F222\r\n* build(deps): bump hono from 4.11.7 to 4.12.0 by @dependabot[bot] in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F224\r\n* 1.9.0 by @husainhirani in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F225\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fcompare\u002Fv1.8.0...v1.9.0","2026-02-23T08:20:52",{"id":108,"version":109,"summary_zh":110,"released_at":111},103987,"v1.8.0","## What's Changed\r\n* feat: improve deployment and build times using SubmitBuild API (#198) by @riddhi-shivhare in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F203\r\n* Increase prettier version to 3.8.0 by @riddhi-shivhare in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F205\r\n* feat: refactoring client generation by @shruti-mantri in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F201\r\n* feat: add support for token based clients by @shruti-mantri in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F206\r\n* fix: upgrade lodash to 4.17.23 by @shruti-mantri in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F209\r\n* 1.8.0 by @husainhirani in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F210\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fcompare\u002Fv1.7.0...v1.8.0","2026-01-27T16:44:09",{"id":113,"version":114,"summary_zh":115,"released_at":116},103988,"v1.7.0","## What's Changed\r\n* Fix link in CONTRIBUTING.md by @steren in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F188\r\n* chore: Modifiy npm publish workflow to trigger on publish by @husainhirani in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F190\r\n* build(deps): bump qs from 6.14.0 to 6.14.1 by @dependabot[bot] in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F194\r\n* Bump express from 5.1.0 to 5.2.1 by @dependabot[bot] in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F180\r\n* test: add stdio and httpstreaming behavior tests for #128 by @riddhi-shivhare in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F200\r\n* feat: Added no build source deploys for NodeJS applications by @husainhirani in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F193\r\n* fix: add additional billing account checks before enabling any api #3 by @riddhi-shivhare in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F196\r\n* build(deps): bump @modelcontextprotocol\u002Fsdk from 1.24.3 to 1.25.2 by @dependabot[bot] in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F197\r\n* fix: increment the cloud-run sdk version by @shruti-mantri in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F202\r\n* 1.7.0 by @husainhirani in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F204\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fcompare\u002Fv1.6.0...v1.7.0","2026-01-16T20:02:27",{"id":118,"version":119,"summary_zh":120,"released_at":121},103989,"v1.6.0","## What's Changed\r\n* 1.5.0 by @steren in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F126\r\n* How to cut a release by @steren in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F127\r\n* feat: support using mcp server on sse mode using GCP_STDIO by @shruti-mantri in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F125\r\n* initial setup for kokoro for integration testing by @shruti-mantri in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F135\r\n* refactor: Modularize codebase by moving and splitting files by @wietsevenema in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F133\r\n* chore: Add unit tests for triggerCloudBuild by @wietsevenema in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F137\r\n* build(coverage): add and configure c8 for coverage checks by @wietsevenema in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F138\r\n* Replace Gemini CLI installation by @steren in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F136\r\n* Readme update by @justinmahood in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F141\r\n* Add login instructions to CLI extension by @steren in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F142\r\n* Modifying the test kokoro build configuration to support execution in RBE clusters by @husainhirani in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F144\r\n* feat: list-services should list run services across all regions by @shruti-mantri in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F146\r\n* Add ToS and Data Processing and Security Terms by @steren in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F149\r\n* feat: provide more getting started instructions for various MCP clients by @shruti-mantri in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F150\r\n* Added script to run deployment presubmit tests by @husainhirani in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F145\r\n* Fixed repository lint by @husainhirani in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F152\r\n* Update GEMINI.md by @gautambaghel in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F155\r\n* feat: Added Github action to run lint check by @husainhirani in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F156\r\n* Fix: Add warning for billing account attachment failure by @riddhi-shivhare in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F160\r\n* feat: Modified project related tests to support Project deletion during the test itself by @husainhirani in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F158\r\n* feat: Implement additional checks for billing account before enabling any Apis by @riddhi-shivhare in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F163\r\n* Fix: Add serviceusage.googleapis.com to required APIs (#166) by @riddhi-shivhare in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F167\r\n* feat: Run end to end integration tests in Kokoro by @husainhirani in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F165\r\n* Bump glob from 10.4.5 to 10.5.0 by @dependabot[bot] in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F173\r\n* Added Antigravity link to MCP configuration documentation. by @steren in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F182\r\n* Revert \"feat: Implement additional checks for billing account\" by @husainhirani in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F185\r\n* Bump mcp sdk to 1.24.3 and add support for Host validation by @husainhirani in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F186\r\n* 1.6.0 by @husainhirani in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F187\r\n\r\n## New Contributors\r\n* @husainhirani made their first contribution in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F144\r\n* @gautambaghel made their first contribution in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F155\r\n* @riddhi-shivhare made their first contribution in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F160\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fcompare\u002Fv1.5.0...v1.6.0","2025-12-11T11:08:09",{"id":123,"version":124,"summary_zh":125,"released_at":126},103990,"v1.5.0","## What's Changed\r\n* fix: correct the gif redirection from README page by @shruti-mantri in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F121\r\n* Bug: Unchecked serviceName parameter leads to a crash in deploy and deployImage by @wietsevenema in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F109\r\n* feat: refactor tools for easily locating registered tools by @shruti-mantri in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F123\r\n\r\n## New Contributors\r\n* @shruti-mantri made their first contribution in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F121\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fcompare\u002Fv1.4.0...v1.5.0","2025-08-28T04:56:47",{"id":128,"version":129,"summary_zh":130,"released_at":131},103991,"v1.4.0","## What's Changed\r\n* Feat\u002Fprogress notifications by @justinmahood in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F93\r\n* fix GEMINI.md capitalization by @steren in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F94\r\n* Open issue before sending PR by @steren in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F101\r\n* Cligif by @justinmahood in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F103\r\n* Use Node test runner for GCP tests by @steren in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F97\r\n* refactor: Remove deploy_local_files tool by @wietsevenema in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F107\r\n* Fix typo in GEMINI.md instructions by @davidstanke in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F115\r\n* v1.4.0 by @justinmahood in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F116\r\n\r\n## New Contributors\r\n* @wietsevenema made their first contribution in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F107\r\n* @davidstanke made their first contribution in https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fpull\u002F115\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-run-mcp\u002Fcompare\u002Fv1.3.0...v1.4.0","2025-08-22T23:02:08",{"id":133,"version":134,"summary_zh":18,"released_at":135},103992,"v1.3.0","2025-08-15T18:36:01",{"id":137,"version":138,"summary_zh":18,"released_at":139},103993,"v1.2.0","2025-08-15T15:55:35",{"id":141,"version":142,"summary_zh":18,"released_at":143},103994,"v1.1.0","2025-08-15T04:39:21",[145,155,165,173,185,193],{"id":146,"name":147,"github_repo":148,"description_zh":149,"stars":150,"difficulty_score":46,"last_commit_at":151,"category_tags":152,"status":63},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",[153,154,56],"开发框架","图像",{"id":156,"name":157,"github_repo":158,"description_zh":159,"stars":160,"difficulty_score":161,"last_commit_at":162,"category_tags":163,"status":63},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",138956,2,"2026-04-05T11:33:21",[153,56,164],"语言模型",{"id":166,"name":167,"github_repo":168,"description_zh":169,"stars":170,"difficulty_score":161,"last_commit_at":171,"category_tags":172,"status":63},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。",107662,"2026-04-03T11:11:01",[153,154,56],{"id":174,"name":175,"github_repo":176,"description_zh":177,"stars":178,"difficulty_score":161,"last_commit_at":179,"category_tags":180,"status":63},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,"2026-04-05T10:45:23",[154,181,182,57,56,183,164,153,184],"数据工具","视频","其他","音频",{"id":186,"name":187,"github_repo":188,"description_zh":189,"stars":190,"difficulty_score":46,"last_commit_at":191,"category_tags":192,"status":63},3128,"ragflow","infiniflow\u002Fragflow","RAGFlow 是一款领先的开源检索增强生成（RAG）引擎，旨在为大语言模型构建更精准、可靠的上下文层。它巧妙地将前沿的 RAG 技术与智能体（Agent）能力相结合，不仅支持从各类文档中高效提取知识，还能让模型基于这些知识进行逻辑推理和任务执行。\n\n在大模型应用中，幻觉问题和知识滞后是常见痛点。RAGFlow 通过深度解析复杂文档结构（如表格、图表及混合排版），显著提升了信息检索的准确度，从而有效减少模型“胡编乱造”的现象，确保回答既有据可依又具备时效性。其内置的智能体机制更进一步，使系统不仅能回答问题，还能自主规划步骤解决复杂问题。\n\n这款工具特别适合开发者、企业技术团队以及 AI 研究人员使用。无论是希望快速搭建私有知识库问答系统，还是致力于探索大模型在垂直领域落地的创新者，都能从中受益。RAGFlow 提供了可视化的工作流编排界面和灵活的 API 接口，既降低了非算法背景用户的上手门槛，也满足了专业开发者对系统深度定制的需求。作为基于 Apache 2.0 协议开源的项目，它正成为连接通用大模型与行业专有知识之间的重要桥梁。",77062,"2026-04-04T04:44:48",[56,154,153,164,183],{"id":194,"name":195,"github_repo":196,"description_zh":197,"stars":198,"difficulty_score":46,"last_commit_at":199,"category_tags":200,"status":63},2181,"OpenHands","OpenHands\u002FOpenHands","OpenHands 是一个专注于 AI 驱动开发的开源平台，旨在让智能体（Agent）像人类开发者一样理解、编写和调试代码。它解决了传统编程中重复性劳动多、环境配置复杂以及人机协作效率低等痛点，通过自动化流程显著提升开发速度。\n\n无论是希望提升编码效率的软件工程师、探索智能体技术的研究人员，还是需要快速原型验证的技术团队，都能从中受益。OpenHands 提供了灵活多样的使用方式：既可以通过命令行（CLI）或本地图形界面在个人电脑上轻松上手，体验类似 Devin 的流畅交互；也能利用其强大的 Python SDK 自定义智能体逻辑，甚至在云端大规模部署上千个智能体并行工作。\n\n其核心技术亮点在于模块化的软件智能体 SDK，这不仅构成了平台的引擎，还支持高度可组合的开发模式。此外，OpenHands 在 SWE-bench 基准测试中取得了 77.6% 的优异成绩，证明了其解决真实世界软件工程问题的能力。平台还具备完善的企业级功能，支持与 Slack、Jira 等工具集成，并提供细粒度的权限管理，适合从个人开发者到大型企业的各类用户场景。",70612,"2026-04-05T11:12:22",[164,56,153,57]]