# awesome-mcp-servers — Directory of MCP Servers > Categorized list of Model Context Protocol (MCP) servers. Use it to discover integrations and build a curated allowlist your team can maintain. ## Install Merge the JSON below into your `.mcp.json`: ## Quick Use ```bash git clone https://github.com/TensorBlock/awesome-mcp-servers cd awesome-mcp-servers rg -n "postgres|github|slack|browser" README.md ``` ## Intro awesome-mcp-servers is a practical starting point for MCP discovery: search by integration need, then validate the repo and pin a small, stable set for production use. **Best for:** Anyone building an MCP stack who needs a discovery index and review workflow **Works with:** MCP clients (Claude Desktop, Claude Code, Cursor, etc.) **Setup time:** 5–20 minutes ### Key facts (verified) - Use ripgrep search on the list to shortlist candidates quickly. - Turn your shortlist into an allowlist with license + activity checks before installing. - GitHub: 675 stars · 383 forks; pushed 2026-05-13 (GitHub API verified). ## Main ### Turn a directory into an operational standard Pick 5–10 core servers, record license/auth/transport, and version-control your `.mcp.json`. ### README excerpt (verbatim) # Awesome MCP Servers  [](https://tensorblock.co) [](https://twitter.com/tensorblock_aoi) [](https://discord.gg/yefvtqDd2w) [](https://huggingface.co/tensorblock) [](https://t.me/TensorBlock)
A comprehensive, community-curated collection of [Model Context Protocol (MCP)](https://modelcontextprotocol.io) servers — covering AI assistants, browser automation, databases, cloud platforms, developer tools, and much more. > **What is MCP?** The Model Context Protocol is an open standard that lets AI models securely connect to external tools, APIs, databases, and filesystems. Think of it as a USB-C port for AI — a universal interface that any model can use to interact with the world. ## Coverage This repo currently includes coverage for **7260 MCP servers as of May 30, 2025**. Due to the limited space, we only show the most recent 30 servers in each category. ## Contributing We welcome submissions! To add your MCP server: 1. Fork this repository 2. Add your server to the relevant category in `README.md`, following the existing format: ``` - [Server Name](https://github.com/owner/repo) - Brief one-sentence description. ``` 3. Open a pull request — we review regularly **Guidelines:** ### FAQ **Q: Should I install servers directly from the list?** A: Shortlist first; then verify repo activity, license, and security posture before installing. **Q: How do I avoid tool sprawl?** A: Pin a curated allowlist and require review for any new server addition. **Q: What’s the fastest way to find a server?** A: Search the README with `rg` for the integration keyword you need. ## Source & Thanks > Source: https://github.com/TensorBlock/awesome-mcp-servers > License: MIT > GitHub stars: 675 · forks: 383 --- ## 快速使用 ```bash git clone https://github.com/TensorBlock/awesome-mcp-servers cd awesome-mcp-servers rg -n "postgres|github|slack|browser" README.md ``` ## 简介 awesome-mcp-servers 适合作为 MCP 发现入口:先按需求搜索,再对仓库做验证与审计,最后把少量稳定 server 固化成生产可用的集合。 **最适合:** 在搭建 MCP 工具栈、需要“发现 + 评审”流程的人 **适配:** 各种 MCP 客户端(Claude Desktop/Claude Code/Cursor 等) **配置时间:** 5–20 分钟 ### 关键事实(已验证) - 通过 ripgrep 搜索清单可快速得到候选短名单。 - 把短名单变成 allowlist:装之前先做许可证与活跃度检查。 - GitHub:675 stars · 383 forks;最近更新 2026-05-13(GitHub API 验证)。 ## 正文 ### 把“目录”变成可运营标准 精选 5–10 个核心 servers,记录许可证/鉴权/传输方式,并把 `.mcp.json` 纳入版本控制。 ### README 原文节选(verbatim) # Awesome MCP Servers  [](https://tensorblock.co) [](https://twitter.com/tensorblock_aoi) [](https://discord.gg/yefvtqDd2w) [](https://huggingface.co/tensorblock) [](https://t.me/TensorBlock) A comprehensive, community-curated collection of [Model Context Protocol (MCP)](https://modelcontextprotocol.io) servers — covering AI assistants, browser automation, databases, cloud platforms, developer tools, and much more. > **What is MCP?** The Model Context Protocol is an open standard that lets AI models securely connect to external tools, APIs, databases, and filesystems. Think of it as a USB-C port for AI — a universal interface that any model can use to interact with the world. ## Coverage This repo currently includes coverage for **7260 MCP servers as of May 30, 2025**. Due to the limited space, we only show the most recent 30 servers in each category. ## Contributing We welcome submissions! To add your MCP server: 1. Fork this repository 2. Add your server to the relevant category in `README.md`, following the existing format: ``` - [Server Name](https://github.com/owner/repo) - Brief one-sentence description. ``` 3. Open a pull request — we review regularly **Guidelines:** ### FAQ **能直接照着清单安装吗?** 答:建议先短名单,再验证仓库活跃度、许可证与安全姿态后安装。 **如何避免工具面膨胀?** 答:维护 allowlist,并对新增 server 强制 review。 **最快怎么找 server?** 答:用 `rg` 在 README 里搜你需要的集成关键词。 ## 来源与感谢 > Source: https://github.com/TensorBlock/awesome-mcp-servers > License: MIT > GitHub stars: 675 · forks: 383 --- Source: https://tokrepo.com/en/workflows/awesome-mcp-servers-directory-of-mcp-servers Author: MCP Hub