upstash/context7

Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

What it solves

Context7 prevents LLMs from generating outdated code or hallucinating APIs by providing them with real-time, version-specific documentation and code examples directly within the prompt context.

How it works

It acts as a bridge between coding agents and a curated index of library documentation. It operates in two primary modes:

  • CLI + Skills: Installs a skill that allows agents to fetch documentation using ctx7 commands.
  • MCP (Model Context Protocol): Registers a server that allows agents to call documentation tools natively to resolve library IDs and query specific docs.

Users can specify library IDs (e.g., /supabase/supabase) or version numbers in their prompts to ensure the agent retrieves the exact documentation needed.

Who it’s for

Developers using AI coding agents (such as Cursor, Claude Code, or OpenCode) who need accurate, up-to-date API references without manually switching tabs to read documentation.

Highlights

  • Version-Specific: Automatically matches the appropriate library version mentioned in the prompt.
  • Multiple Integration Paths: Supports both a CLI-based approach and the Model Context Protocol (MCP).
  • Direct Context Injection: Places documentation straight into the LLM's context to eliminate hallucinations.
  • Broad Compatibility: Provides manual installation guides for over 30 different MCP clients.

Related

  • Project
    neuledge/context

    An MCP server that provides AI agents with instant, local, and up-to-date documentation for 100+ popular libraries to prevent hallucinations caused by outdated training data.

  • Project
    MicrosoftDocs/mcp

    An MCP server that gives AI assistants direct, secure access to official Microsoft documentation and code samples to eliminate hallucinations and provide up-to-date technical data.

  • Project
    NeoLabHQ/context-engineering-kit

    A plug‑in marketplace for LLM‑based coding assistants (Claude Code, Gemini, Antigravity, etc.) that supplies token‑efficient, context‑engineering patterns—reflection loops, sub‑agent judges, specification‑first development, code‑review agents, and Git helpers—to make AI‑generated code more reliable and easier to integrate into CI pipelines.

  • Project
    langchain-ai/mcpdoc

    An MCP server that provides AI agents with a transparent and auditable way to fetch documentation via llms.txt files.

  • Project
    awslabs/mcp

    Open‑source MCP (Model Context Protocol) servers that let LLM‑powered tools fetch live AWS documentation, IaC guidance, and safely invoke AWS APIs. Includes managed remote servers and local binaries for docs, IaC, EKS, etc., all accessed via a stdio‑based protocol.