Gemini Docs MCP Server

MCP server for retrieving relevant documentation from a knowledge base

Local serverstdioGo

What is the Gemini Docs MCP server?

MCP server for retrieving relevant documentation from a knowledge base. That is what the gemini docs mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

This project implements an MCP server that enables access to documentation for various technologies using the Gemini API with its gigantic context window of 2M tokens. It should work for any client, but is targeted especially to the Roo/Cline environment.

  • Enables clients to take an "ask your docs" approach to learning and debugging for an arbitrary number of technologies, including some obscure or lesser-known ones
  • Uses the Gemini API to answer questions about the documentation
  • Supports multiple tools for querying the documentation:
  • can_x_be_done: Check if a specific task can be done in a given technology
  • hints_for_problem: Get hints for solving a specific problem
  • is_this_good_practice: Check if a code snippet follows good practices

The tools it exposes

The server publishes 2 tools. What each one is for:

  • Input — ** docs, prompt, x, technology
  • Output — ** success, data

Getting it running

Installation goes through your MCP client rather than a global install: point it at @smithery/cli on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

What it needs from you

Configuration is passed through the environment: GEMINI_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

How it compares

Plenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Gemini Docs's toolset — Input, Output — is a fair guide to whether it matches your workflow. It is maintained by M-Gonzalo; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
Input** docs, prompt, x, technology
Output** success, data

How to install the Gemini Docs MCP server

{
  "mcpServers": {
    "cosa-sai": {
      "command": "npx",
      "args": ["-y", "@smithery/cli"],
      "env": {
        "GEMINI_API_KEY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
GEMINI_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Gemini Docs to Input.
  • Use Gemini Docs to Output.

Frequently asked questions

No. The knowledge base is static and must be manually updated to reflect changes in the technology.