{"id":30004698,"url":"https://github.com/tencent-rtc/mcp","last_synced_at":"2026-02-28T19:01:51.203Z","repository":{"id":306934445,"uuid":"1008183803","full_name":"Tencent-RTC/mcp","owner":"Tencent-RTC","description":"This improves the LLM AI Agent's ability to understand and interact with Tencent RTC SDKs and APIs.","archived":false,"fork":false,"pushed_at":"2025-07-28T13:18:31.000Z","size":359,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-08-05T07:33:12.806Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Tencent-RTC.png","metadata":{"files":{"readme":"README-zh_CN.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-06-25T06:48:49.000Z","updated_at":"2025-07-30T11:48:17.000Z","dependencies_parsed_at":"2025-07-28T15:17:10.197Z","dependency_job_id":"e8921a49-894b-4321-99c6-ee5dc4f25920","html_url":"https://github.com/Tencent-RTC/mcp","commit_stats":null,"previous_names":["tencent-rtc/mcp"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Tencent-RTC/mcp","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Tencent-RTC%2Fmcp","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Tencent-RTC%2Fmcp/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Tencent-RTC%2Fmcp/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Tencent-RTC%2Fmcp/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Tencent-RTC","download_url":"https://codeload.github.com/Tencent-RTC/mcp/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Tencent-RTC%2Fmcp/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29948228,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-28T18:42:55.706Z","status":"ssl_error","status_checked_at":"2026-02-28T18:42:48.811Z","response_time":90,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-08-05T07:18:57.806Z","updated_at":"2026-02-28T19:01:51.170Z","avatar_url":"https://github.com/Tencent-RTC.png","language":null,"readme":"## 腾讯 SDK 模型上下文协议 (MCP) 服务器，用于 Cursor IDE\n\n该仓库提供了一个基于命令行界面（CLI）的模型上下文协议 (MCP) 服务器，它将腾讯 SDK 文档和腾讯 API 资源暴露给由 LLM 驱动的工具。这提升了 LLM AI 智能体理解和与腾讯 SDK 及 API 交互的能力。\n\n## 功能特性\n\n* MCP 服务器通过 STDIN/STDOUT 上的 JSON-RPC 暴露工具，用于与腾讯交互。\n* 检索以下语言的腾讯官方 SDK 文档（HTML → Markdown）：\n    * 语言：JavaScript、Java、Swift、Objective-C、Kotlin。\n    * API 参考部分：配置、调用函数。\n* 检索腾讯官方 TUICallKit SDK 文档（HTML → Markdown），支持：\n    * TUICallKit SDK 语言：JavaScript、Kotlin、Swift。\n    * TUICallKit SDK 主题：配置、调用函数。\n* 使用 `jsdom` 和 `turndown` 将远程 HTML 文章转换为 Markdown，以确保文档格式一致性。\n* 通过 Zod schema 对所有工具参数进行输入验证，确保强大的错误处理能力。\n* 利用模型上下文协议 SDK (`@modelcontextprotocol/sdk`) 及其 `McpServer` 和 `StdioServerTransport`，实现可扩展的工具定义。\n\n## 先决条件\n* Node.js (版本 \u003e= 18) 和 npm\n* 支持 MCP 的 Cursor 、 CodeBuddy、Trae 等 IDE\n\n## 如何使用\n要设置 `@tencentcloud/sdk-mcp` MCP 服务器，请遵循以下步骤：\n\n### 步骤 1：安装。\n\n```\nnpx -y @tencentcloud/sdk-mcp\n```\n\n### 步骤 2：MCP 配置。\n\n在您的 Cursor 项目中，创建或打开 `.cursor/mcp.json` 或 `~/.cursor/mcp.json` 文件并添加您的配置。\n\n```json\n{\n  \"mcpServers\": {\n    \"tencentcloud-sdk-mcp\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@tencentcloud/sdk-mcp\"],\n      \"env\": {\n        \"SDKAPPID\": \"YOUR_SDKAPPID\",\n        \"SECRETKEY\": \"YOUR_SECRET_KEY\"\n      }\n    }\n  }\n}\n```\n当您保存文件时，将显示一个通知。在提示中，点击 **启用 (Enable)**。\n\n### 步骤 3：检查 MCP 状态。\n导航到 Cursor 设置（右上角的齿轮图标）-\u003e MCP，并检查 tencentcloud-sdk-mcp 服务器是否已启用。\n\n### 步骤 4：使用 MCP。\n通过描述功能或使用示例提示，让 AI 智能体为您构建您的腾讯云 SDK 应用程序。\n\n\u003e [!NOTE]\n如果需要获取更多详情信息，请点击 [AI 接入](https://cloud.tencent.com/document/product/269/124481)\n\n\u003e [!WARNING]\n根据您的 IDE 规则，您可能还需要明确要求 AI 智能体使用 `tencentcloud-sdk-mcp` server。","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftencent-rtc%2Fmcp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftencent-rtc%2Fmcp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftencent-rtc%2Fmcp/lists"}