Google MCP Tools
Seamless Google Workspace integration for AI-driven clients via the MCP protocol
Key Features
Use Cases
README
Google MCP Tools
This is a collection of Google-native tools (e.g., Gmail, Calendar) for the MCP protocol, designed to integrate seamlessly with AI clients like Claude or Cursor.
Quick Install
Click below for one-click install with .mcpb:
{
"mcpServers": {
"google-mcp": {
"command": "bunx",
"args": ["--no-cache", "google-mcp@latest"],
"env": {
// Either can be used, but not both
// Use OAuth
"GOOGLE_OAUTH_CLIENT_ID": "<YOUR_CLIENT_ID>",
"GOOGLE_OAUTH_CLIENT_SECRET": "<YOUR_CLIENT_SECRET>",
"GOOGLE_OAUTH_TOKEN_PATH": "<PATH_TO_STORE_TOKENS> CAN_BE_ANYWHERE_ON_YOUR_SYSTEM",
// Use Service Account
"GOOGLE_CLIENT_EMAIL": "<YOUR_SERVICE_ACCOUNT_EMAIL>",
"GOOGLE_PRIVATE_KEY": "<YOUR_SERVICE_ACCOUNT_PRIVATE_KEY>",
"GMAIL_USER_TO_IMPERSONATE": "<USER_TO_IMPERSONATE>"
}
}
}
}
What's New in v1.1.0
🆕 Major Features
- Complete Email Attachment Support:
- ✉️ Send emails with attachments from local files or Google Drive
- 📥 Download all email attachments to local storage
- 🔄 Dual attachment sources: Local file paths or Google Drive file IDs
- 📁 Smart file handling: Automatic MIME type detection and filename sanitization
🔧 Enhanced Email Capabilities
- Multi-source attachments: Attach files from local storage or Google Drive in the same email
- Custom filenames: Override original filenames for attachments
- File size validation: Automatic 25MB Gmail limit enforcement
- Cross-platform downloads: Auto-detection of Downloads folder on Windows, macOS, and Linux
- Conflict resolution: Automatic file renaming to prevent overwrites
📁 New & Enhanced Tools
google_gmail_send_email: Now supports attachments from local files and Google Drivegoogle_gmail_draft_email: Create drafts with attachmentsgoogle_gmail_download_attachments: Download all email attachments with customizable path
Features
-
OAuth Management:
- Refresh expired access tokens automatically
- Update tokens in the token file without re-authentication
- Complete re-authentication with automated token cleanup
- Maintain session continuity across long-running operations
-
Gmail:
- Send emails with multiple recipients (to, cc, bcc) and attachments from local files or Google Drive.
- Download all email attachments to local storage with cross-platform support.
- List emails with custom queries, labels, and result limits.
- Read specific emails by ID with attachment information.
- Manage labels (add, remove, list).
- Draft and delete emails.
-
Calendar:
- List calendars and set a default calendar.
- Create events with details (summary, start/end time, attendees, etc.).
- List upcoming events with customizable filters.
- Update or delete existing events.
- Find free time slots for scheduling.
-
Drive:
- Filter with search queries
- Sort by modification date or other criteria
- Customize display count
- View detailed file metadata
- Read file content (text, docs, spreadsheets)
- Create new files with specified content
- Update existing files
- Delete files (trash or permanent)
- Share files with specific permissions
-
Tasks:
- View all task lists
- Create new task lists
- Delete existing task lists
- Set default task list
- List tasks with filters
- View task details
- Create tasks with title, notes, and due dates
- Update task properties
- Mark tasks as complete
- Delete tasks
-
TODO Plans:
- Google Contacts: Search and manage contacts.
- And Many More...
You can chain commands for workflows, e.g.:
"List my unread emails, draft a reply to the latest one, and schedule a follow-up meeting tomorrow at 2 PM."
OAuth Token Management
The server includes built-in OAuth token management to handle expired access tokens gracefully:
- Automatic Token Refresh: When access tokens expire, you can refresh them without going through the full OAuth flow again
- Complete Re-authentication: Automatically handle cases where refresh tokens are invalid or expired
- Persistent Storage: Refreshed tokens are automatically saved to your configured token file path
- Session Continuity: All Google services are re-initialized with fresh tokens after refresh
Refreshing Tokens
If you encounter authentication errors or want to proactively refresh your tokens, simply ask:
Refresh my Google OAuth tokens
This will:
- Use your stored refresh token to get new access tokens
- Update the token file with the new credentials
- Re-initialize all Google services with fresh authentication
- Show you the new token expiration time
Complete Re-authentication
If you get invalid_grant errors or your refresh token has expired, you can start fresh:
Re-authenticate my Google account
This automated process will:
- Delete existing tokens from your token file
- Start OAuth server to handle the callback
- Open browser for fresh authentication
- Save new tokens automatically
- Re-initialize services with fresh credentials
You'll only need to click "Allow" in the browser - everything else is automated!
Note: If you don't have a valid refresh token, you'll need to go through the initial OAuth authentication flow again.
Manual Installation
-
Prerequisites:
- Install Bun:
bashbrew install oven-sh/bun/bun # macOS/Linux with Homebrew -
Set Up OAuth:
- Create a Google Cloud project in the Google Cloud Console.
- Set up OAuth 2.0 credentials (Client ID, Client Secret).
- Choose the type Desktop app.
- If using test mode, add your email to the test users list.
- Make sure to enable API access for desired services (Gmail, Calendar, Drive etc.).
-
Configure Your Client: Edit your claude_desktop_config.json (or equivalent config file for your client):
{
"mcpServers": {
"google-mcp": {
"command": "bunx",
"args": ["--no-cache", "google-mcp@latest"],
"env": {
// Either can be used, but not both
// Use OAuth
"GOOGLE_OAUTH_CLIENT_ID": "<YOUR_CLIENT_ID>",
"GOOGLE_OAUTH_CLIENT_SECRET": "<YOUR_CLIENT_SECRET>",
"GOOGLE_OAUTH_TOKEN_PATH": "<PATH_TO_STORE_TOKENS>",
// Use Service Account
"GOOGLE_CLIENT_EMAIL": "<YOUR_SERVICE_ACCOUNT_EMAIL>",
"GOOGLE_PRIVATE_KEY": "<YOUR_SERVICE_ACCOUNT_PRIVATE_KEY>",
"GMAIL_USER_TO_IMPERSONATE": "<USER_TO_IMPERSONATE>"
}
}
}
}
- Authenticate:
- The first time you run the server, it will open a browser for OAuth authentication. Follow the prompts to grant access, and tokens will be saved to GOOGLE_OAUTH_TOKEN_PATH.
Usage
Now, ask Claude to use the google-mcp tool.
Send an email to jane.doe@example.com with the subject "Meeting Notes" and body "Here are the notes from today."
List my upcoming calendar events for the next 3 days.
Create a calendar event titled "Team Sync" tomorrow at 10 AM for 1 hour.
Refresh my Google OAuth tokens
Re-authenticate my Google account
Transport Support
This MCP server supports both stdio and HTTP transports via environment variables:
Stdio Transport (Default)
# Default mode - uses stdio transport
bun run dev
# Or explicitly
MCP_TRANSPORT=stdio bun run index.ts
HTTP Transport (Streamable HTTP)
# HTTP mode with Streamable HTTP support
MCP_TRANSPORT=http bun run index.ts
# Or with custom port
MCP_TRANSPORT=http PORT=3000 bun run index.ts
When running in HTTP mode, the server provides these endpoints:
GET /health- Health check endpoint with session countGET /mcp- Session info and server statusPOST /mcp- Main MCP JSON-RPC endpoint for sending requestsDELETE /mcp- End session endpoint
Session Management
The Streamable HTTP transport uses the official MCP SDK with automatic session management:
- Automatic Sessions: The server automatically generates secure session IDs
- SSE Streaming: Supports Server-Sent Events for real-time communication
- JSON Responses: Falls back to JSON responses when SSE is not available
- DNS Protection: Built-in security features for production deployment
Configuration for HTTP Transport
For HTTP transport, configure your client with the server URL:
{
"mcpServers": {
"google-mcp-http": {
"url": "http://localhost:3000/mcp"
}
}
}
Local Development
git clone https://github.com/vakharwalad23/google-mcp.git
cd google-mcp
bun install
# Run in stdio mode (default)
bun run dev:stdio
# Run in HTTP mode
bun run dev:http
Thank you for using Google MCP Tools! If you have any questions or suggestions, feel free to open an issue or contribute to the project.
Play around with the tools and enjoy!!
Star History
Repository Owner
User
Repository Details
Programming Languages
Tags
Topics
Join Our Newsletter
Stay updated with the latest AI tools, news, and offers by subscribing to our weekly newsletter.
Related MCPs
Discover similar Model Context Protocol servers
MyMCP Server (All-in-One Model Context Protocol)
Powerful and extensible Model Context Protocol server with developer and productivity integrations.
MyMCP Server is a robust Model Context Protocol (MCP) server implementation that integrates with services like GitLab, Jira, Confluence, YouTube, Google Workspace, and more. It provides AI-powered search, contextual tool execution, and workflow automation for development and productivity tasks. The system supports extensive configuration and enables selective activation of grouped toolsets for various environments. Installation and deployment are streamlined, with both automated and manual setup options available.
- ⭐ 93
- MCP
- nguyenvanduocit/all-in-one-model-context-protocol
keep-mcp
Connect Google Keep notes to the Model Context Protocol ecosystem.
Provides an MCP server interface for Google Keep, enabling standardized interaction with Keep notes via the Model Context Protocol. Allows users to search, create, update, and delete Google Keep notes through MCP, supporting integration with MCP-compatible platforms. It restricts modification and deletion operations to notes managed by the MCP server unless configured otherwise. Credentials for Google authentication are securely handled through environment variables.
- ⭐ 52
- MCP
- feuerdev/keep-mcp
Klavis
One MCP server for AI agents to handle thousands of tools.
Klavis provides an MCP (Model Context Protocol) server with over 100 prebuilt integrations for AI agents, enabling seamless connectivity with various tools and services. It offers both cloud-hosted and self-hosted deployment options and includes out-of-the-box OAuth support for secure authentication. Klavis is designed to act as an intelligent connector, streamlining workflow automation and enhancing agent capability through standardized context management.
- ⭐ 5,447
- MCP
- Klavis-AI/klavis
TickTick MCP Server
Enable powerful AI-driven task management for TickTick via the Model Context Protocol.
TickTick MCP Server provides comprehensive programmatic access to TickTick task management features using the Model Context Protocol. Built on the ticktick-py library, it enables AI assistants and MCP-compatible applications to create, update, retrieve, and filter tasks with improved precision and flexibility. The server supports advanced filtering, project and tag management, subtask handling, and robust context management for seamless AI integration.
- ⭐ 35
- MCP
- jen6/ticktick-mcp
Azure MCP Server
Connect AI agents with Azure services through Model Context Protocol.
Azure MCP Server provides a seamless interface between AI agents and Azure services by implementing the Model Context Protocol (MCP) specification. It enables integration with tools like GitHub Copilot for Azure and supports a wide range of Azure resource management tasks directly via conversational AI interfaces. Designed for extensibility and compatibility, it offers enhanced contextual capabilities for agents working with Azure environments.
- ⭐ 1,178
- MCP
- Azure/azure-mcp
TickTick MCP
MCP server for AI-powered TickTick task management integration
TickTick MCP is a Model Context Protocol (MCP) server that enables standardized integration of TickTick's task management features with AI assistants and developer applications. It allows programmatic access to create, update, retrieve, complete, or delete tasks and projects in TickTick via Python. Using this MCP server, AI systems can leverage TickTick's API to help automate and manage user's to-do lists and projects through natural language or other interfaces.
- ⭐ 6
- MCP
- ekkyarmandi/ticktick-mcp
Didn't find tool you were looking for?