Google Tasks MCP Server

What does “Google Tasks” MCP Server do?

The Google Tasks MCP (Model Context Protocol) Server is a specialized tool designed to bridge AI assistants with Google Tasks, allowing seamless integration between AI-driven workflows and task management. By exposing Google Tasks as an MCP server, it enables AI clients to list, read, search, create, update, and delete tasks directly through standardized protocol actions. This integration facilitates automation and organization by allowing developers or end-users to manage their Google Tasks database from within AI-enhanced environments, streamlining productivity workflows, and enabling more complex task-driven agentic behaviors. The server is especially useful for those looking to automate personal or team task management, synchronize reminders, or build custom productivity tools that interact with Google Tasks via secure and standardized interfaces.

List of Prompts

No prompt templates are explicitly mentioned in the repository or documentation.

Ready to grow your business?

Start your free trial today and see results within days.

Request demo Log in

List of Resources

• Tasks (gtasks:///<task_id>):
  Represents individual tasks in Google Tasks. Each resource supports reading task details such as title, status, due date, notes, and other metadata. Tasks can be listed, created, updated, or deleted using the provided tools.

List of Tools

• search:
  Search for tasks in Google Tasks by query string. Returns matching tasks with details.
• list:
  List all tasks in Google Tasks, with optional pagination.
• create:
  Create a new task with optional task list ID, title, notes, and due date.
• update:
  Update an existing task’s details including title, notes, status, or due date.
• delete:
  Delete a task from a specific task list.
• clear:
  Clear completed tasks from a Google Tasks list.

Join our newsletter

Get latest tips, trends, and deals for free.

Email address

Subscribe

Use Cases of this MCP Server

• Automated task management:
  Enable AI assistants to automatically create, update, and clean up tasks based on conversational context or workflow triggers, reducing manual task entry.
• Productivity workflow automation:
  Integrate with developer or team workflows to synchronize Google Tasks with project milestones, reminders, or issue trackers.
• Personal assistant integrations:
  Allow virtual assistants (like Claude) to manage daily to-dos, mark tasks as complete, or remind users of due tasks by interacting directly with Google Tasks.
• Custom productivity tool development:
  Developers can build AI-powered dashboards or bots that leverage Google Tasks for task tracking and management.
• Bulk operations on tasks:
  Quickly clear completed tasks or perform mass updates using AI-driven logic, saving time on repetitive actions.

How to set it up

Windsurf

1. Prerequisites: Ensure Node.js is installed and server is built (npm run build or npm run watch).
2. Prepare OAuth keys: Place your gcp-oauth.keys.json in the repo root.
3. Edit configuration: Locate Windsurf’s configuration file for MCP servers.
4. Add server: Insert the following JSON snippet to the mcpServers object:

   {
     "mcpServers": {
       "gtasks": {
         "command": "/opt/homebrew/bin/node",
         "args": [
           "{ABSOLUTE PATH TO FILE HERE}/dist/index.js"
         ]
       }
     }
   }
   

5. Save & restart: Save the config and restart Windsurf to load the server.

Securing API keys

Use environment variables for sensitive data:

{
  "env": {
    "GOOGLE_CLIENT_ID": "your-client-id",
    "GOOGLE_CLIENT_SECRET": "your-client-secret"
  },
  "inputs": {
    ...
  }
}

Claude

1. Prerequisites: Install Node.js and build the server as above.
2. Authenticate: Run npm run start auth and complete OAuth in your browser.
3. Locate config: Edit Claude’s MCP server configuration.
4. Add server: Use the JSON snippet below:

   {
     "mcpServers": {
       "gtasks": {
         "command": "/opt/homebrew/bin/node",
         "args": [
           "{ABSOLUTE PATH TO FILE HERE}/dist/index.js"
         ]
       }
     }
   }
   

5. Restart & verify: Restart Claude and ensure the server is available.

Securing API keys

{
  "env": {
    "GOOGLE_CLIENT_ID": "your-client-id",
    "GOOGLE_CLIENT_SECRET": "your-client-secret"
  }
}

Cursor

1. Install Node.js and build the server.
2. Set up OAuth (as above) and credentials.
3. Find the configuration file for MCP servers in Cursor.
4. Insert the following:

   {
     "mcpServers": {
       "gtasks": {
         "command": "/opt/homebrew/bin/node",
         "args": [
           "{ABSOLUTE PATH TO FILE HERE}/dist/index.js"
         ]
       }
     }
   }
   

5. Save, restart, and test.

Securing API keys

{
  "env": {
    "GOOGLE_CLIENT_ID": "your-client-id",
    "GOOGLE_CLIENT_SECRET": "your-client-secret"
  }
}

Cline

1. Ensure prerequisites: Node.js, server build (npm run build).
2. Prepare OAuth keys and credentials.
3. Locate Cline’s config for MCP servers.
4. Add MCP server:

   {
     "mcpServers": {
       "gtasks": {
         "command": "/opt/homebrew/bin/node",
         "args": [
           "{ABSOLUTE PATH TO FILE HERE}/dist/index.js"
         ]
       }
     }
   }
   

5. Save, restart, and verify.

Securing API keys

{
  "env": {
    "GOOGLE_CLIENT_ID": "your-client-id",
    "GOOGLE_CLIENT_SECRET": "your-client-secret"
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "gtasks": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “gtasks” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Between these two tables, Google Tasks MCP is a focused, practical server with strong tool and resource support, but lacks prompt templates and explicit sampling/roots support. Based on the available information, I would rate this MCP server a 7/10 for practical utility and completeness.

MCP Score