mcp-gemini-docs
A MCP server that provides AI assistants with access to the Gemini API documentation.
claude mcp add --transport stdio amaansyed27-mcp-gemini-docs node /absolute/path/to/mcp-gemini-docs/gemini-docs-mcp/build/index.js
How to use
This MCP server provides AI assistants with access to the Gemini API documentation. It serves the content from the gemini-api-docs directory and exposes a search capability via the search_docs tool, allowing you to quickly locate topics, guides, and API references directly within your chat interface. Once configured in your MCP client, you can ask the assistant to read specific docs, browse sections, or perform topic searches across the Gemini docs. The server runs locally (or wherever you host it) and is designed to be compatible with Claude Desktop, Cursor, VS Code integrations, and any MCP-compliant client.
To use it effectively, ensure your client points to the Node server built from gemini-docs-mcp/build/index.js. Use the search_docs tool to query the documentation, and request full doc passages or summaries as needed. The server serves static Markdown docs, so you’ll get fast local access without network latency, making it ideal for brainstorming, integration work, or offline documentation review.
How to install
Prerequisites:
- Node.js v16 or higher installed on your machine
- NPM comes with Node.js
- A clone of the repository containing the gemini-docs-mcp server and the gemini-api-docs docs folder
Installation steps:
-
Clone the repository (if not already): git clone <repository-url> cd mcp-gemini-docs
-
Install dependencies and build the server: cd gemini-docs-mcp npm install npm run build
-
Ensure the built server is accessible at the expected path:
- The server entrypoint should be at gemini-docs-mcp/build/index.js
- The gemini-api-docs content should be available under gemini-api-docs/ in the repository
-
Configure your MCP client to point to the server using the provided commands in the README. See the configuration examples for Claude, Antigravity (VS Code), Cursor, Copilot, and CLI tools.
Notes:
- If you relocate the repository, update the absolute path in your MCP configuration accordingly.
Additional notes
Tips and considerations:
- Use the exact absolute path to the built index.js when configuring MCP clients (e.g., /absolute/path/to/mcp-gemini-docs/gemini-docs-mcp/build/index.js).
- The server serves documentation from gemini-api-docs; ensure this directory exists and contains the content you expect to expose.
- When integrating with different MCP clients, you may need to adjust the JSON keys and path references to match client-specific MCP config formats.
- If you modify docs, re-run npm run build to ensure the latest changes are served.
- If you encounter port or binding issues, confirm there’s no other process occupying the expected port and that network access to the local machine is allowed by the client configuration.
Related MCP Servers
gemini-cli
An open-source AI agent that brings the power of Gemini directly into your terminal.
anytype
An MCP server enabling AI assistants to interact with Anytype - your encrypted, local and collaborative wiki - to organize objects, lists, and more through natural language.
gemini
MCP Server that enables Claude code to interact with Gemini
apitap
The MCP server that turns any website into an API — no docs, no SDK, no browser. npm: @apitap/core
hackmd
A Model Context Protocol server for integrating HackMD's note-taking platform with AI assistants.
mcp-gemini
This project provides a dedicated MCP (Model Context Protocol) server that wraps the @google/genai SDK. It exposes Google's Gemini model capabilities as standard MCP tools, allowing other LLMs (like Cline) or MCP-compatible systems to leverage Gemini's features as a backend workhorse.