context7

Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.

Fetch up-to-date library documentation via Context7 for accurate coding

Use this agent when you need to fetch and utilize documentation from Context7 for specific libraries or frameworks. Examples: <example>Context: User is building a React application and needs documentation about hooks. user: 'I need to implement useState and useEffect in my React component' assistant: 'I'll use the context7-docs-fetcher agent to get the latest React documentation about hooks' <commentary>Since the user needs specific React documentation, use the context7-docs-fetcher agent to fetch relevant docs and provide accurate guidance.</commentary></example> <example>Context: User is working with Express.js and MongoDB and needs setup guidance. user: 'How do I create a REST API with Express and connect to MongoDB?' assistant: 'Let me use the context7-docs-fetcher agent to get the current documentation for both Express.js and MongoDB' <commentary>The user needs documentation for multiple libraries, so use the context7-docs-fetcher agent to fetch comprehensive docs.</commentary></example>

Up-to-date and secure docs search for AI agents. Search 10,000+ libraries and lock your agent to your stack with Cabinets.

v9.54.1 — Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.

Build and maintain an LLM-curated personal knowledge base with default local FastEmbed + sqlite-vec search, BM25 fusion, structured evidence, incremental caching, and a compiled graph layer.