Google Tasks
Integrate with Google Tasks to manage your to-do lists and tasks.
Google Tasks MCP Server
This Model Context Protocol (MCP) server provides a bridge between Claude and Google Tasks, allowing you to manage your task lists and tasks directly through Claude.
[!NOTE] All (bar some edits) code in this project was "vibe coded" - generated with Claude/Copilot with instructions from me.
Features
This MCP server provides the following functionality:
Task List Management
list-tasklists- List all your task listsget-tasklist- Get details about a specific task listcreate-tasklist- Create a new task listupdate-tasklist- Update an existing task listdelete-tasklist- Delete a task list
Task Management
list-tasks- List all tasks in a task listget-task- Get details about a specific taskcreate-task- Create a new taskupdate-task- Update an existing taskdelete-task- Delete a taskcomplete-task- Mark a task as completedmove-task- Move a task (reorder or change parent)clear-completed-tasks- Clear all completed tasks from a list
Setup Instructions
1. Create Google Cloud Project & Enable API
- Go to the Google Cloud Console
- Create a new project
- Navigate to "APIs & Services" > "Library"
- Search for "Google Tasks API" and enable it
- Go to "APIs & Services" > "Credentials"
- Click "Create Credentials" > "OAuth Client ID"
- Configure the OAuth consent screen (External is fine for personal use)
- For Application Type, select "Web application"
- Add "http://localhost:3000/oauth2callback" as an authorized redirect URI
- Create the client ID and secret
2. Configure Claude for Desktop
- Install Claude for Desktop
- Open the Claude configuration file:
- MacOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
- MacOS:
- Add the Google Tasks MCP server configuration:
{
"mcpServers": {
"google-tasks": {
"command": "node",
"args": ["/path/to/google-tasks-mcp/build/index.js"],
"env": {
"GOOGLE_CLIENT_ID": "your_client_id_here",
"GOOGLE_CLIENT_SECRET": "your_client_secret_here",
"GOOGLE_REDIRECT_URI": "http://localhost:3000/oauth2callback"
}
}
}
}
Replace the path and credentials with your own values.
Environment Variables:
GOOGLE_CLIENT_ID(required) - Your Google OAuth Client IDGOOGLE_CLIENT_SECRET(required) - Your Google OAuth Client SecretGOOGLE_REDIRECT_URI(optional) - OAuth redirect URI (defaults tohttp://localhost:3000/oauth2callback)
Note: The server validates that GOOGLE_CLIENT_ID and GOOGLE_CLIENT_SECRET are set at startup and will fail with clear error messages if they are missing or invalid.
3. Build and Run the Server
- Install dependencies:
npm install
- Build the server:
npm run build
- Restart Claude for Desktop
Authentication Flow
When you first use the Google Tasks MCP server:
- Use the
authenticatetool to get an authorization URL - Visit the URL in your browser and sign in with your Google account
- After authorizing, you'll receive a code on the browser page
- Use the
set-auth-codetool with this code to complete authentication - You can now use all other tools to interact with Google Tasks
Note: Your authentication tokens (including refresh tokens) are automatically saved to disk at ~/.config/google-tasks-mcp/credentials.json with restricted permissions (600). This means:
- You only need to authenticate once - credentials persist across server restarts
- Automatic token refresh - Access tokens are automatically refreshed when they expire (typically after 1 hour) using the saved refresh token
- No re-authentication needed - After the initial setup, you won't need to authenticate again unless you revoke access or delete the credentials file
Requirements
- Node.js 20+ (see
package.jsonengines) - Claude for Desktop (latest version)
- Google Cloud Project with Tasks API enabled
Implementation Features
This MCP server includes the following improvements:
- Persistent token storage - Authentication credentials are saved to disk (
~/.config/google-tasks-mcp/credentials.json) with restricted permissions, so you only need to authenticate once - Environment variable validation - Startup validation ensures required credentials are configured with clear error messages
- Automatic token refresh - OAuth tokens are automatically refreshed when they expire, eliminating the need to re-authenticate during active sessions or after restarts
- Enhanced input validation - Comprehensive validation of all inputs including ID formats, string lengths, and RFC 3339 date formats
- HTML sanitization - OAuth callback responses are sanitized to prevent XSS vulnerabilities
- Graceful shutdown - Proper cleanup of resources on SIGINT/SIGTERM signals
- Type safety - Full TypeScript type safety throughout the codebase with proper interfaces
- Configurable redirect URI - The OAuth redirect URI can be customized via the
GOOGLE_REDIRECT_URIenvironment variable
Screenshots
Claude Desktop

Cursor

License
This project is for demonstration purposes only. Use at your own risk.
Related Servers
Gorev
A powerful, Go-based task management server with MCP support, AI editor integration, and a VS Code extension. It supports smart task creation, markdown, and project organization.
Pleasanter MCP Server
An MCP server for interacting with the Pleasanter low-code/no-code business application platform.
Quire MCP Server
Interact with Quire.io projects and tasks using the Quire API, enabling AI assistants to manage your workflow.
Obsidian MCP Server
An MCP server that allows AI assistants to read from and write to your local Obsidian vault.
MCP Fleet
A Python monorepo for AI-powered project management and productivity servers, utilizing the Claude API.
X CRM MCP
Give AI the context of your X followers with CRM functionality
TanukiMCP
Automate and manage WordPress sites using browser automation and API integration.
Feishu/Lark OpenAPI
Connect AI agents with the Feishu/Lark platform for automation, including document processing, conversation management, and calendar scheduling.
Hyperweb
A server for interacting with the Hyperweb platform and its tools using AI agents.
Tmux
Interact with your Tmux sessions, windows and pane, execute commands in tmux panes and retrieve result.