Up-to-date code documentation for LLMs and AI code editors, eliminating outdated or hallucinated API references.
context7 is easy to set up with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
gh repo view upstash/context7 --webOpen the official README and confirm the supported install method.
Add the server entry to your MCP client config.
Restart your agent and verify that the server tools appear.
Context7 fetches the latest documentation and code examples for libraries and frameworks directly into your AI coding assistant's context. It works as a CLI tool or MCP server, so your agent always has accurate, version-specific information without switching tabs.
Context7 is a platform that provides up-to-date code documentation and examples for LLMs and AI code editors. It solves the problem of AI models relying on outdated or hallucinated API information by pulling fresh documentation from official sources directly into the prompt. The tool supports two modes: CLI + Skills mode, which installs a skill that guides the agent to fetch docs using 'ctx7' commands (no MCP required), and MCP mode, which registers a Context7 MCP server for native tool calls. It integrates with popular coding agents like Cursor, Claude Code, and OpenCode. Context7 is built by Upstash and is open-source under the MIT license. The repository is a monorepo containing packages for the CLI, MCP server, and AI SDK tools.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 12 days ago.
56435 GitHub stars indicate community interest.
153 open issues signal maintenance load.
MIT license detected.
Fetching the latest Next.js middleware documentation for JWT authentication.
Getting up-to-date Cloudflare Worker caching examples.
Retrieving current Supabase auth API details for email/password sign-up.
Ensuring AI code generation uses correct, non-hallucinated API calls.
Providing version-specific documentation for any library or framework.
56,435
Stars
2,666
Forks
153
Issues
MIT
License
Official MCP reference servers from Anthropic. Includes servers for filesystem, GitHub, Postgres, Slack, and more.
Zero-dependency, token-efficient MCP server for querying multiple databases via a single interface.
A secure MCP server for AI applications to interact with MySQL databases.
0 security/trust notes recorded.
Setup difficulty is 2/5.