This server provides search and retrieval tools for Google Gemini API documentation through an MCP (Model Context Protocol) interface.
Available Tools:
search_documentation: Performs keyword-based, full-text searches across all Gemini documentation pages using short queries (1-3 keywords maximum, max 3 queries at once)get_capability_page: Retrieves the complete content of a specific documentation page by its exact title, or call without arguments to get a master list of all available page titlesget_current_model: Quickly accesses the dedicated "Gemini Models" documentation page with details about model variants (Pro, Flash, etc.), their capabilities, versioning, and context window sizes
Key Features:
Automatic documentation updates on server startup by scraping from
ai.google.devLocal SQLite database with FTS5 full-text search indexing for efficient querying and offline access
Supports Python and TypeScript SDK documentation
Provides tools for searching and retrieving Google Gemini API documentation, including full-text search across documentation pages, listing available capabilities, and accessing current model documentation.
Gemini Docs MCP Server
An local STDIO MCP server that provides tools to search and retrieve Google Gemini API documentation.
Search Documentation: Full-text search across all Gemini documentation pages.
Get Capabilities: List available documentation pages or retrieve content for a specific page.
Get Current Model: Quickly access documentation for current Gemini models.
Automatic Updates: Scrapes and updates documentation on server startup.
How it Works
Ingestion: On startup, the server fetches
https://ai.google.dev/gemini-api/docs/llms.txtto get a list of all available documentation pages.Processing: It then concurrently fetches and processes each page, extracting the text content.
Indexing: The processed content is stored in a local SQLite database with a Full-Text Search (FTS5) index for efficient querying.
Searching: When you use the
search_documentationtool, the server queries this SQLite database to find the most relevant documentation pages.
Installation
Option 1: Use uvx (Recommended)
You can use uvx to run the server directly without explicit installation. This is the easiest way to get started.
Option 2: Install directly from GitHub
You can install the package directly from GitHub using pip:
Option 3: Manual Installation (for development)
Usage
If you installed via pip (Option 2 or 3), run the server using:
This will start the MCP server over stdio. It will immediately begin ingesting documentation, which might take a few moments on the first run.
Configuration
The database is stored at ~/.mcp/gemini-api-docs/database.db by default. You can override this by setting the GEMINI_DOCS_DB_PATH environment variable.
Using with an MCP Client
Configure your MCP client to run the gemini-docs-mcp command.
Tools
search_documentation(queries: list[str]): Performs a full-text search on Gemini documentation for the given list of queries (max 3).get_capability_page(capability: str = None): Get a list of capabilities or content for a specific one.get_current_model(): Get documentation for current Gemini models.
License
MIT
Test Results
We run a comprehensive evaluation harness to ensure the MCP server provides accurate and up-to-date code examples. The tests cover both Python and TypeScript SDKs.
Metric | Value |
Total Tests | 117 |
Passed | 114 |
Failed | 3 |
Last updated: 2025-11-03 13:29:01
You can find the detailed test results in tests/result.json.