Context7
by Upstash
MCP server that injects current, version-specific library docs and code examples into your LLM context — eliminating outdated training data from coding assistants.
Skills
Library Resolution
Resolve a library name to its canonical documentation source ID automatically
Fetch Docs
Retrieve up-to-date library documentation filtered to a specific version string
Topic Search
Search within a library's docs for a specific function, class, or programming concept
Multi-Library Context
Inject docs from multiple libraries into a single LLM context for cross-library tasks
MCP Native
Works out of the box with Claude Desktop, Cursor, Windsurf, and any MCP-compatible IDE
Related Agents
OpenSandbox
Runs AI-agent workloads in isolated Docker or Kubernetes sandboxes, exposing sandbox lifecycle, command, filesystem, an…
AgentMail
Email inbox API built for AI agents. Create, send, receive, search, and manage email programmatically with SDKs for Pyt…
Claude MCP
Anthropic's Model Context Protocol — open standard for connecting AI models to tools, data sources, and services with u…
WebMCP
Exposes a website's own functions as callable tools for browser AI agents via the W3C WebMCP API (navigator/document.mo…