Google Docs

Overview

Google Docs is a Model Context Protocol server that lets AI systems read and edit Google Docs directly. Any MCP-compatible AI assistant can access Google Docs tools during conversations or agent runs, with the model deciding when to use them.

The server runs locally via the npm package google-documents-mcp, communicating over stdio. You'll need to set environment variables for GOOGLE_ACCESS_TOKEN, MCP_TRANSPORT, and GOOGLE_CLIENT_ID. The latest release is v1.2.0, published by domdomegg and available on GitHub at domdomegg/google-documents-mcp.

Google Docs is categorized as Development on mcp.site and integrates with MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed, and others. If you maintain this project, claim your listing to verify ownership and keep information up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "google_docs": {
      "command": "npx",
      "args": [
        "-y",
        "google-documents-mcp"
      ],
      "env": {
        "GOOGLE_ACCESS_TOKEN": "<google-access-token>",
        "MCP_TRANSPORT": "<mcp-transport>",
        "GOOGLE_CLIENT_ID": "<google-client-id>",
        "GOOGLE_CLIENT_SECRET": "<google-client-secret>"
      }
    }
  }
}

Requires GOOGLE_ACCESS_TOKEN, MCP_TRANSPORT, GOOGLE_CLIENT_ID