Skip to main content
MCP server CX Codex

Gemini API Docs — Claude Code MCP server: what it does, how to install

A local stdio MCP server that keeps a copy of the Gemini API docs in SQLite so your agent can search them offline.

no license updated 2026-10-29

Open on GitHub

What Gemini API Docs does

The server answers from a local index instead of the web. On startup it fetches the page list from https://ai.google.dev/gemini-api/docs/llms.txt, downloads every page, strips the text and writes it into SQLite with an FTS5 index. Lookups hit that database.

Three tools ship with it. search_documentation takes up to three queries per call, get_capability_page returns the section list or the body of one section, and get_current_model serves the page about the current Gemini models. Ingestion starts right away, so the first launch is slow and the server answers nothing until it finishes.

The database lives at ~/.mcp/gemini-api-docs/database.db unless GEMINI_DOCS_DB_PATH points elsewhere. Going through uvx skips installation entirely. With the pip route you start gemini-docs-mcp yourself afterwards, otherwise the server never comes up.

What it helps with

  • look up the embeddings example in the Gemini API docs
  • check which Gemini model is current without leaving the editor
  • list the doc sections and pull the text of one page
  • keep a local docs index that refreshes on every startup
  • have the agent cite the official page instead of guessing

Example prompts for the agent

  • Search the Gemini API documentation for how request batching works
  • Show me the current Gemini model page from the docs server
  • List the capability pages and open the one on embeddings

How to install Gemini API Docs

Install

The MCP registry has no launch command for it: see the repository README

Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more

Questions about Gemini API Docs

How do I install Gemini API Docs in Claude Code?

Run uvx --from git+https://github.com/philschmid/gemini-api-docs-mcp gemini-docs-mcp and nothing needs installing first. Then put the same command with its arguments into the mcpServers block of your MCP client config.

What does Gemini API Docs do?

It builds a local SQLite index of the Gemini API documentation and exposes three tools to the agent: full-text search, capability pages, and the page for current models.

What does the server need to run?

Reachability of https://ai.google.dev/gemini-api/docs/llms.txt at startup, since the index is rebuilt from that list each time. The SQLite file can be relocated with GEMINI_DOCS_DB_PATH.

Similar MCP servers

All MCP servers for Agent setup: memory, context, orchestration →

Project sponsors

Companies that keep this analytics open