Context7 is an MCP server that injects up-to-date, version-specific library documentation directly into LLM prompts. Add "use context7" to any coding prompt and it fetches current docs for the library you're working with, eliminating hallucinated APIs and outdated code examples. Works with Claude Desktop, Cursor, Windsurf, and any MCP-compatible editor.

Context7

Active·★ 62.8k·MIT·Updated 2026-10-08

★ Most Popular★ Trending★ Essential

Context7, by Upstash, feeds up-to-date, version-specific library documentation and code examples into your AI coding assistant's context. It addresses a common failure of LLMs: code based on year-old training data, hallucinated APIs and answers written for old package versions.

It is useful for anyone using Cursor, Claude Code, OpenCode or other coding agents with fast-moving libraries. You can add "use context7" to a prompt, name a specific library ID such as /vercel/next.js to skip the matching step, or mention a version (for example Next.js 14) to get matching docs. It works in two modes: a CLI plus skill (`ctx7`) that guides the agent to fetch docs without MCP, or an MCP server that exposes resolve-library-id and query-docs tools.

Getting started: run `npx ctx7 setup` (Node.js 18+), which signs you in with OAuth, creates an API key and installs the skill or MCP configuration for your agent; flags such as `--cursor` and `--claude` target a specific client. You can also point any MCP client at https://mcp.context7.com/mcp with your API key. A free API key gives higher rate limits.

#LLM#Code Generation#API Documentation#Developer Tools#Model Context Protocol#Coding

Features

01Fetches current, version-specific library documentation on demand

02Add "use context7" to any prompt — zero additional configuration

03Covers thousands of popular libraries with up-to-date docs

04Works as a hosted MCP server (no local install required)

05Integrates with Claude Desktop, Cursor, Windsurf, and VS Code

Why choose it

+Directly reduces hallucinated APIs and outdated examples by grounding the agent in current, version-specific docs.

+Very low setup effort: one command configures the major coding agents.

+Works with or without MCP (CLI plus skill mode), and with 30+ MCP clients.

+Large community-contributed library index, and library authors can submit their own projects.

Trade-offs

!Only the MCP server is open source; the API backend, parsing engine and crawler are private, so you depend on Upstash's hosted service.

!Documentation is community-contributed, and the project itself does not guarantee its accuracy, completeness or security.

!Requests go to an external service, which may matter for teams with strict data policies; heavier use needs an API key for higher rate limits.

Compatibility

Claude Desktop

Native

Verified via docs

Cursor

Native

Verified via docs

Windsurf

Supported

Verified via docs

VS Code

Supported

Verified via docs

Quick start

$ npx ctx7 setup

Use cases

↳Preventing LLMs from hallucinating deprecated or non-existent API methods

↳Getting accurate code examples for the exact library version in use

↳Keeping AI coding assistants up-to-date across fast-moving frameworks

How it compares

≈vs Apple Docs MCP and other single-source docs servers: those cover one ecosystem in depth; Context7 covers many libraries through one interface.

≈vs letting the agent browse the web: Context7 returns curated docs and snippets matched to a library and version, which is usually faster and less noisy than general web fetching.

≈vs adding docs to your repo as context files: Context7 keeps docs current without you maintaining copies, at the cost of relying on an external service.

Alternatives

Gemini CLI★ 107.3k

An open-source AI agent that brings the power of Gemini directly into your terminal. Supports native MCP.

vs →

Open Interpreter★ 68.5k

A coding agent for the terminal, optimized for low-cost and open models. Forked from OpenAI's Codex, it can emulate other agent harnesses and runs commands in a native sandbox.

vs →

ragflow★ 91.9k

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

GitHub MCP Server★ 33.5k

GitHub's official MCP Server. Allows AI agents to interact directly with your GitHub repositories (read files, search code, issues).

n8n★ 206.7k

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

Brave Search MCP★ 1.5k

Allow your AI Agent to search the real-time internet using Brave Search API. Essential for getting up-to-date information.

Microsoft AutoGen★ 61.3k

A framework that enables the development of LLM applications using multiple agents that can converse with each other to solve tasks.

CrewAI★ 59.5k

Framework for orchestrating role-playing, autonomous AI agents. By working together, your Crew can tackle complex tasks.

See all alternatives →

Comments

No comments yet. Be the first!

Context7

Active·★ 62.8k·MIT·Updated 2026-10-08

★ Most Popular★ Trending★ Essential

#LLM#Code Generation#API Documentation#Developer Tools#Model Context Protocol#Coding

Features

01Fetches current, version-specific library documentation on demand

02Add "use context7" to any prompt — zero additional configuration

03Covers thousands of popular libraries with up-to-date docs

04Works as a hosted MCP server (no local install required)

05Integrates with Claude Desktop, Cursor, Windsurf, and VS Code

Why choose it

+Directly reduces hallucinated APIs and outdated examples by grounding the agent in current, version-specific docs.

+Very low setup effort: one command configures the major coding agents.

+Works with or without MCP (CLI plus skill mode), and with 30+ MCP clients.

+Large community-contributed library index, and library authors can submit their own projects.

Trade-offs

!Only the MCP server is open source; the API backend, parsing engine and crawler are private, so you depend on Upstash's hosted service.

!Documentation is community-contributed, and the project itself does not guarantee its accuracy, completeness or security.

!Requests go to an external service, which may matter for teams with strict data policies; heavier use needs an API key for higher rate limits.

Compatibility

Claude Desktop

Native

Verified via docs

Cursor

Native

Verified via docs

Windsurf

Supported

Verified via docs

VS Code

Supported

Verified via docs

Quick start

$ npx ctx7 setup

Use cases

↳Preventing LLMs from hallucinating deprecated or non-existent API methods

↳Getting accurate code examples for the exact library version in use

↳Keeping AI coding assistants up-to-date across fast-moving frameworks

How it compares

≈vs Apple Docs MCP and other single-source docs servers: those cover one ecosystem in depth; Context7 covers many libraries through one interface.

≈vs letting the agent browse the web: Context7 returns curated docs and snippets matched to a library and version, which is usually faster and less noisy than general web fetching.

≈vs adding docs to your repo as context files: Context7 keeps docs current without you maintaining copies, at the cost of relying on an external service.