MCP Configs2026年3月31日·1 分钟阅读

Context7 — Up-to-Date Docs MCP for AI Editors

MCP server that provides AI code editors with up-to-date library documentation. Eliminates hallucinations from outdated training data. Supports 1000+ libraries. 51K+ stars.

TO
TokRepo精选 · Community
快速使用

先拿来用，再决定要不要深挖

这里应该同时让用户和 Agent 知道第一步该复制什么、安装什么、落到哪里。

{
  "mcpServers": {
    "context7": {
      "command": "npx",
      "args": ["-y", "@context7/mcp@latest"]
    }
  }
}

Add to your Claude Code, Cursor, or Windsurf MCP config. Then ask: "Using context7, show me how to use React Server Components."

介绍

Context7 is an MCP server that gives AI code editors access to up-to-date, version-specific library documentation. Instead of relying on outdated training data, your AI assistant fetches real documentation for React, Next.js, Python, Node.js, and 1,000+ other libraries in real-time. Eliminates code hallucinations caused by stale API knowledge. 51,000+ GitHub stars, MIT licensed.

Best for: Any developer using AI coding tools who wants accurate, current documentation Works with: Claude Code, Cursor, Windsurf, Gemini CLI, any MCP client

How It Works

  1. You ask your AI assistant about a library (e.g., "How do I use Next.js App Router?")
  2. Context7 MCP fetches the latest documentation for that library version
  3. AI generates code based on current docs — not outdated training data

Why It Matters

  • React 19 patterns differ from React 18 — training data may be stale
  • Next.js 15 App Router has different APIs than Pages Router
  • Python 3.12 has features LLMs don't know about

Supported Libraries

1,000+ libraries indexed and updated continuously: React, Next.js, Vue, Svelte, Angular, Node.js, Express, FastAPI, Django, Flask, TailwindCSS, Prisma, Drizzle, PostgreSQL, MongoDB, Redis, Docker, Kubernetes, Terraform, AWS SDK, and many more.

FAQ

Q: What is Context7? A: An MCP server providing AI code editors with real-time, up-to-date library documentation. Eliminates hallucinations from stale training data. 1,000+ libraries supported. 51K+ stars.

Q: Does it slow down my AI responses? A: Minimal latency — documentation is pre-indexed and cached. Most lookups complete in under 500ms.

🙏

来源与感谢

Created by Upstash. Licensed under MIT. upstash/context7 — 51,000+ GitHub stars

相关资产

MLC-LLM — Universal LLM Deployment Engine

Deploy any LLM on any hardware — phones, browsers, GPUs, CPUs. Compiles models for native performance on iOS, Android, WebGPU, CUDA, Metal, and Vulkan. 22K+ stars.

TokRepo精选

OpenAI Swarm — Lightweight Multi-Agent Orchestration

Educational multi-agent framework by OpenAI. Ergonomic agent handoffs, tool calling, and context variables. Minimal abstraction over Chat Completions API. 21K+ stars.

TokRepo精选

Supabase MCP — Database & Auth for AI Agents

Official Supabase MCP server. Connect AI agents to Supabase for database queries, auth management, storage, edge functions, and real-time subscriptions. 2.6K+ stars.

TokRepo精选
◈首页🏆Trending👤我的