Gmail MCP

What is Gmail MCP?

Gmail MCP is a server implementation that enables AI assistants to interact with Gmail through the Model Context Protocol (MCP). It provides tools for sending emails, managing drafts, reading emails, searching through your inbox, and managing Gmail labels. It uses OAuth2.0 authentication with the Gmail API.

How to use Gmail MCP?

Set up a Google Cloud Platform project with the Gmail API enabled, download OAuth credentials as credentials/client_secret_gmail_oauth.json, and install Python dependencies using uv. Then configure your MCP client to point to the server with uv run main.py. On first run, you will be prompted to authenticate with your Gmail account.

Key features of Gmail MCP

• Send emails and create drafts
• Read and search emails
• Delete emails
• Manage Gmail labels (create, update, delete)
• OAuth2.0 authentication with Gmail API

Use cases of Gmail MCP

• AI assistant composing and sending emails on behalf of a user
• Searching and summarizing recent emails from the inbox
• Managing labels to categorize threads automatically
• Deleting unwanted emails programmatically

FAQ from Gmail MCP

What are the prerequisites?

Python 3.11 or higher, a Gmail account, a Google Cloud Platform project with the Gmail API enabled, and the uv package installer.

How do I set up OAuth credentials?

Create a project in Google Cloud Console, enable the Gmail API, create OAuth credentials, download the JSON file, and save it as credentials/client_secret_gmail_oauth.json in the project root.

What MCP clients are supported?

The server works with any MCP‑compatible client. Specific client integration instructions should be sought from the client’s official documentation.

How does authentication work?

The server uses OAuth 2.0. On first run, it prompts the user to authenticate with their Gmail account.

What runtime dependencies are required?

All dependencies are listed in requirements.txt and installed via uv pip install -r requirements.txt. The server is invoked using uv run main.py.