Google Tasks MCP Server
Enables AI assistants to manage Google Tasks through natural language interactions. Supports creating, updating, deleting, searching, and listing tasks with secure OAuth2 authentication.
README
Google Tasks MCP Server
A Model Context Protocol (MCP) server for Google Tasks integration in Claude Desktop. This server enables AI assistants to manage Google Tasks through natural language interactions.
Forked from Zach Caceres' (zcaceres) original implementation to enhance authentication handling, add support for multiple task lists, and provide a more robust npm package with Smithery integration for Claude Desktop. This fork is fully functional and properly deployed on Smithery, making it ready for immediate use with Claude.
Features
- List all tasks in your Google Tasks lists
- Search for specific tasks by query
- Create new tasks with title, notes, and due date
- Update existing tasks (title, notes, status, due date)
- Delete tasks
- Clear completed tasks from a task list
- Full integration with Google Tasks API
- Secure OAuth2 authentication
- Docker support for containerized deployment
Task Creation Example
Here's a simple example of task creation using natural language with Claude:

With just a simple instruction like "create a task named 'eat a banana in the morning'", Claude can instantly create the task in your Google Tasks.
Installation
Installing via Smithery
To install Google Tasks Integration for Claude Desktop automatically:
npx -y @smithery/cli install @alvincrave/gtasks-mcp --client claude
Manual Installation
npm install @alvincrave/gtasks-mcp
Setup
-
Create a Google Cloud Project and obtain credentials:
a. Create a Google Cloud Project:
- Go to Google Cloud Console
- Create a new project or select an existing one
- Enable the Google Tasks API for your project
b. Create OAuth 2.0 Credentials:
- Go to "APIs & Services" > "Credentials"
- Click "Create Credentials" > "OAuth client ID"
- Choose "Desktop app" as application type
- Give it a name and click "Create"
- You will get your
GOOGLE_CLIENT_IDandGOOGLE_CLIENT_SECRET
c. Get Refresh Token:
- Go to OAuth 2.0 Playground
- Click the gear icon (Settings) in the top right
- Check "Use your own OAuth credentials"
- Enter your OAuth Client ID and Client Secret
- In the left panel, find "Tasks API v1" and select "https://www.googleapis.com/auth/tasks"
- Click "Authorize APIs" and complete the OAuth flow
- Click "Exchange authorization code for tokens"
- Copy the "Refresh token" - this is your
GOOGLE_REFRESH_TOKEN
-
Configure in Claude Desktop:
{
"mcpServers": {
"gtasks": {
"command": "npx",
"args": ["-y", "@alvincrave/gtasks-mcp"],
"env": {
"GOOGLE_CLIENT_ID": "your_client_id_here",
"GOOGLE_CLIENT_SECRET": "your_client_secret_here",
"GOOGLE_REFRESH_TOKEN": "your_refresh_token_here"
},
"connectionTypes": ["stdio"],
"autoRestart": true
}
}
}
Docker Support
You can run this server in a Docker container:
# Build the Docker image
docker build -t gtasks-mcp .
# Run the container
docker run -p 3000:3000 \
-e GOOGLE_CLIENT_ID=your_client_id \
-e GOOGLE_CLIENT_SECRET=your_client_secret \
-e GOOGLE_REFRESH_TOKEN=your_refresh_token \
gtasks-mcp
Usage Examples
The server provides several tools that can be used through Claude Desktop:
Search Tasks
search for tasks containing "meeting"
List Tasks
show me all my tasks
Create Task
create a task to "Prepare presentation" due on Friday
Update Task
mark the "Send email" task as completed
Delete Task
delete the task about "old project"
Clear Completed Tasks
clear all completed tasks from my list
Security Notes
- Keep your Google API credentials secure
- Regularly rotate your refresh tokens
- Store sensitive information in Claude Desktop configuration
- Never share or commit your credentials to version control
- The refresh token gives access to your Google Tasks, treat it like a password
License
This project is licensed under the MIT License.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.