Context7 MCP Server

Up-to-date documentation and code examples from source to your AI prompts.

Data last scanned today · Reviewed yesterday

632 tools★ 59,415TypeScriptMIT

Overview

Context7 serves as a bridge for LLMs, providing real-time, version-specific documentation and code examples. By fetching current data directly from source, it mitigates the risk of hallucinated APIs or outdated library syntax that often occurs when models rely on stale training data. Developers can integrate this into their workflows to generate accurate code for specific frameworks, such as Next.js or Cloudflare Workers. The server ensures that the context provided to your AI assistant reflects the latest package documentation available.

Our verdict

The Context7 MCP Server receives a high-risk security score of 38/100, primarily due to the lack of any authentication method, meaning anyone with the configuration can utilize the server. Additionally, the tool does not implement a read-only mode, which could pose access concerns for some users. Due to these significant security gaps, it is recommended only for users who fully understand the implications of an unauthenticated, open configuration environment.

Fetches real-time, version-specific documentation from source
Reduces hallucinated APIs and stale code examples
Supports multiple languages via internationalized documentation
Maintained with a low dependency count of two

No authentication mechanisms implemented
Lacks a read-only execution mode
Community-maintained rather than official vendor software

Setup

Claude Desktop

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

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows), then restart Claude Desktop. Some servers require API keys or tokens as environment variables — check the project's README and add an "env" object if needed.

No read-only mode — running this grants full read/write access.
No built-in authentication — anyone with access to this config can invoke every tool it exposes.

Tools

Tool	Description	Risk
resolve-library-id	Resolves a general library name into a Context7-compatible library ID.	low
query-docs	Retrieves documentation for a library using a Context7-compatible library ID.	low