Context7
Up-to-date documentation for any library injected straight into the agent context — no more stale-API code.
Overview
Usage is simple: add use context7 to a prompt, or let the agent call it automatically whenever it works with a library — it pulls the relevant docs pages and examples for the pinned version. The result is code written against the current API instead of training-data guesses.
It became one of the most-used MCP servers in the world because it measurably improves generated-code accuracy with fast-moving frameworks like Next.js, Astro and Tailwind.
Who Is This For?
- Developers on fast-moving frameworks like Next.js and Astro
- Teams suffering from generated code that targets removed APIs
- Developers learning a new library who want official examples
- Any project on versions newer than what the model knows
Installation
Add to .claude/settings.json:
{"mcpServers":{"context7":{"command":"npx","args":["-y","@upstash/context7-mcp"]}}} Configuration
CONTEXT7_API_KEY=ctx7_xxxx (optional — raises rate limits) Explore AI Tools
Discover the best AI tools that complement your skills
Read AI & Design Articles
Tips and trends in the world of design and AI
Related Servers
Linear MCP Server
Manage Linear issues, projects, and workflows directly from your AI coding agent without leaving the terminal.
Playwright MCP
Automate browser interactions and run end-to-end tests through the Model Context Protocol, enabling AI agents to verify UI behavior in real browsers.
Jest Test Runner
Run, debug, and analyze Jest test suites directly from your AI agent. Quickly identify failing tests and get suggested fixes.