upstash/context7

Project overview

Context7 injects current, version-specific library documentation and code examples into LLM prompts, addressing hallucinated or outdated API usage. It operates as an MCP server or CLI tool integrated into coding agents, relying on a private backend for document retrieval.

Project type

MCP · AI Coding

Use cases

Knowledge Q&A · Coding & Development

Deployment

Refer to project documentation

License

MIT

Best for

• Developers engaged in AI-assisted coding who need current library documentation and code examples without leaving their coding environment.

Key capabilities

• Registers a Context7 MCP server, enabling an agent to call documentation tools including resolve-library-id and query-docs natively.
• Installs a skill that directs an agent to fetch documentation using ctx7 CLI commands.
• Automatically matches appropriate library versions based on user prompt mentions.
• Authenticates via OAuth, generates an API key, and installs the appropriate skill for specific coding agents.

Limitations and risks

• The supporting API backend, parsing engine, and crawling engine are private and are not part of the project repository.
• Context7 projects are community-contributed; the accuracy, completeness, or security of all library documentation cannot be guaranteed.

Getting started

• Run npx ctx7 setup, authenticate via OAuth, and start using Context7 in the agent prompt. Requires Node.js 18 or newer.

Evidence and sources

• README: @upstash/context7-mcp - MCP server
• README: LLMs rely on outdated or generic information about the libraries you use.
• README: Context7 pulls up-to-date, version-specific documentation and code examples straight from the source — and places them directly into your prompt.
• README: resolve-library-id: Resolves a general library name into a Context7-compatible library ID.
• README: CLI + Skills — installs a skill that guides your agent to fetch docs using `ctx7` CLI commands (no MCP required)

Reviewed at: 2026-07-17T06:18:07Z