Context7
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Context7What's the latest documentation for the requests library in Python?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Context7 MCP server
Install Context7 MCP server in Claude Code:
claude mcp add --scope user --transport http context7 https://mcp.context7.ai/mcpRestart Claude Code, then claude mcp list. You want context7 in that list.
Same command on context7.ai.
Installation
That command is the install. --scope user puts it in every project. Leave the flag off if you only want the current repo.
Optional API key (rate limits, private repos). Make one at context7.ai/dashboard, then:
claude mcp add --scope user --header "Authorization: Bearer YOUR_API_KEY" --transport http context7 https://mcp.context7.ai/mcp
Claude Desktop, Cursor, VS Code, Windsurf
JSON config: under mcpServers, add context7 with type http and url https://mcp.context7.ai/mcp. Drop-in files: examples/claude_desktop_config.json, examples/cursor.json, examples/vscode.json, examples/windsurf.json.
Claude Code plugin: plugins/claude/context7. Skill: skills/context7-mcp/SKILL.md. MCP registry manifest: server.json.
Remote HTTP vs local npx: this page is the remote. npx ctx7 setup and npx -y @upstash/context7-mcp are the local/stdio path. I use the remote so I do not run another Node process.
Related MCP server: MCP Framework Documentation Server
Usage
Ask for something library-specific and add use context7 to the prompt.
Tools
Once it is connected you get Context7's tools, resolve-library-id and query-docs.
Troubleshooting
context7 mcp not connecting / context7 mcp server not found: run claude mcp list. Missing means the add did not stick, or you skipped the restart. Listed but dead usually means you added both mcp.context7.ai and mcp.context7.com under the same name.
spawn context7-mcp ENOENT is a local stdio install that cannot find a binary. Use the remote HTTP command above.
Links
Install page: context7.ai
License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
@latest documentation and code examples to 9000+ libraries for LLMs and AI code editors in a singl…
Team docs served to AI agents over MCP - search, Markdown reads, version pinning, read audit.
Pay-per-use tool marketplace for AI agents. Search, price-check, and call APIs via MCP.
Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceProvides up-to-date, version-specific documentation and code examples for software libraries directly to LLMs, enabling resolution of library identifiers and retrieval of relevant documentation with code snippets.-
- AlicenseAqualityDmaintenanceProvides tools for AI agents to search, browse, and retrieve the full documentation for the mcp-framework. It enables agents to access documentation sections and page content directly within MCP-compatible environments like Claude Code and Cursor.36 npmMIT
- AlicenseAqualityDmaintenanceEnables managing internal documentation with search and add capabilities, and fetching official documentation from 13+ popular libraries via MCP tools.69MIT
- AlicenseNot gradedqualityDmaintenanceProvides MCP tools to list and search OpenAI Agents SDK documentation, enabling LLMs to retrieve documentation topics and content via natural language queries.MIT