Google Tasks MCP Server

Overview

Google Tasks MCP Server enables you to manage Google Tasks directly from any MCP-compatible AI client. Instead of switching between apps, your AI assistant can read, create, update, and organize tasks in conversation—the model decides when and how to use these capabilities based on what you're working on.

The server runs locally via the Python package google-tasks-mcp, installed with uvx google-tasks-mcp. You'll authenticate with Google by providing GOOGLE_CLIENT_ID, GOOGLE_CLIENT_SECRET, and GOOGLE_REDIRECT_URI as environment variables. Version v0.4.0 is the latest release, distributed under the Apache-2.0 license with source code available at ebmurha/google-tasks-mcp on GitHub.

Listed under AI & Agents, Google Tasks MCP Server works with MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed, and others. If you maintain this server, claim your listing to verify ownership and keep information accurate.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "google_tasks_mcp_server": {
      "command": "uvx",
      "args": [
        "google-tasks-mcp"
      ],
      "env": {
        "GOOGLE_CLIENT_ID": "<google-client-id>",
        "GOOGLE_CLIENT_SECRET": "<google-client-secret>",
        "GOOGLE_REDIRECT_URI": "<google-redirect-uri>"
      }
    }
  }
}

Requires GOOGLE_CLIENT_ID, GOOGLE_CLIENT_SECRET, GOOGLE_REDIRECT_URI