Context7
Up-to-date docs for LLMs and AI code editors
About Context7
Context7 provides up-to-date code examples and documentation for LLMs and AI code editors. Its MCP connector brings current library context into assistant workflows, reducing tab switching and helping generated code avoid outdated APIs, nonexistent methods, and stale implementation patterns.
What can you do with the Context7 MCP server
- Context7 resolves a general library name into a Context7-compatible library ID.
- Context7 retrieves relevant documentation using an exact library ID and a user question or task.
- Context7 places up-to-date, version-specific documentation and code examples into the assistant's context.
- Context7 can match documentation for a specified library version.
- Context7 can skip library matching when the prompt includes an exact Context7 library ID.
Common use cases
- Use Context7 to create Next.js middleware that validates a JWT cookie and redirects unauthenticated users.
- Use Context7 to configure a Cloudflare Worker to cache JSON API responses for five minutes.
- Use Context7 to find guidance for migrating from Next.js 15 to Next.js 16.
- Use Context7 to retrieve the Supabase email and password sign-up API documentation.
Before you connect
- Manual MCP setup requires configuring https://mcp.context7.com/mcp in an MCP client and passing an API key in the CONTEXT7_API_KEY header.
- An API key is recommended for higher rate limits and is available from the Context7 dashboard.
- The optional ctx7 CLI setup path requires Node.js 18 or newer.
Connection details
https://mcp.context7.com/mcp- Transport
- Streamable HTTP
- Authentication
- OAuth
Setup
claude mcp add context7 --transport http https://mcp.context7.com/mcpLimitations
- Context7 does not guarantee the accuracy, completeness, or security of community-contributed library documentation.
- Projects listed in Context7 are developed and maintained by their respective owners, not by Context7.
- The API backend, parsing engine, and crawling engine are private and are not included in the MCP server source repository.
Frequently asked questions
What is the Context7 remote MCP server?
The Context7 remote MCP server is a hosted Model Context Protocol endpoint at https://mcp.context7.com/mcp, so AI assistants can connect to it without installing or running anything locally. Context7 provides up-to-date code examples and documentation for LLMs and AI code editors. Its MCP connector brings current library context into assistant workflows, reducing tab switching and helping generated code avoid outdated APIs, nonexistent methods, and stale implementation patterns.
How do I connect to the Context7 MCP server?
Add the endpoint https://mcp.context7.com/mcp to any MCP-compatible client such as Claude Code, Codex, Cursor, or VS Code. The setup snippets on this page configure each client in one step.
Does the Context7 MCP server require authentication?
Yes. Context7 uses OAuth: the first time you connect, your MCP client opens a browser window to sign in and authorize access, then reuses the credentials for future sessions.
Which transport does the Context7 MCP server use?
Context7 exposes a Streamable HTTP endpoint, the current standard transport for the Model Context Protocol, supported by all major MCP clients.
More remote MCP servers

