1. Conduid
  2. Developer Tools
  3. Gmail MCP
MCP server · Developer Tools

Gmail MCP

A Gmail service implementation using MCP (Model Context Protocol) that provides functionality for sending, receiving, and managing emails through Gmail's API.

Unclaimed last commit a year ago devtools
37Low

Scored 8 days ago · breakdown

About Gmail MCP

Gmail MCP is an MCP server published by gangradeamitesh in the Developer Tools category: a Gmail service implementation using MCP (Model Context Protocol) that provides functionality for sending, receiving, and managing emails through Gmail's API.

The repository has 6 stars and 2 forks, with the last commit a year ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues before depending on it in production.

Install

From source
git clone https://github.com/gangradeamitesh/mcp-google-email

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Gmail MCP

Powered by Claude · Grounded in docs

I know everything about Gmail MCP. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

Static checks derived from the repository 9 days ago. Heuristics on the source, not an audit.

  • ✓README presentThe repository ships documentation.
  • !License declaredNo license file. Legally you have no right to use it in a product.
  • !Tests presentNo tests found. Behaviour changes may go unnoticed between versions.
  • ✓Dependencies pinnedA lockfile pins dependency versions.
  • ✓No dynamic code executionSource scan found no eval, dynamic Function, or shell execution.
  • !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.

Releases

release_0_1_10.1.1 · 30 May 2025

README

MCP Google Email Service

A Gmail service implementation using MCP (Model Context Protocol) that provides functionality for sending, receiving, and managing emails through Gmail's API.

Motivation and Context

The MCP Google Email Service was developed to address several key needs in modern application development:

  1. Standardized Email Integration: Provides a consistent interface for Gmail integration across different applications, eliminating the need to write boilerplate code for Gmail API interactions.

  2. Simplified Authentication: Handles the complexity of Gmail API authentication through multiple methods (Service Account, OAuth 2.0, and Application Default Credentials), making it easier to integrate Gmail functionality into applications.

  3. Environment-Based Configuration: Supports flexible configuration through environment variables, making it suitable for various deployment scenarios (development, staging, production).

  4. Model Context Protocol (MCP) Integration: Implements the Model Context Protocol, ensuring consistent behavior and integration with other MCP-compliant services. MCP provides a standardized way to handle context and state management across different services.

This service is particularly useful for:

  • Applications requiring automated email handling
  • Systems needing to integrate Gmail functionality
  • Projects requiring a standardized way to interact with Gmail
  • Services that need to maintain email communication logs
  • Applications requiring real-time email processing
  • LLM applications needing email context management

Features

  • Email sending and receiving
  • Message listing with search capabilities
  • Reply to existing messages
  • Today's message retrieval
  • Multiple authentication methods support
  • Environment-based configuration

Installation

pip install mcp-google-email

Usage

from src.server import FastMCP

# Initialize the Gmail service
gmail_service = FastMCP("GMail")

# List unread messages
messages = gmail_service.list_message(query='is:unread', max_results=10)

# Send an email
gmail_service.send_message(
    to='recipient@example.com',
    subject='Test Email',
    message_text='Hello, this is a test email'
)

# Get today's messages
todays_messages = gmail_service.get_todays_messages(max_results=20)

# Reply to a message
gmail_service.reply_to_message(
    message_id='message_id_here',
    reply_text='Thank you for your email'
)

Authentication

The package supports multiple authentication methods:

  1. Service Account (via GOOGLE_APPLICATION_CREDENTIALS or GOOGLE_CREDENTIALS_CONFIG)
  2. OAuth 2.0 (via credentials.json and token.json)
  3. Application Default Credentials (ADC)

Environment Variables

The following environment variables can be used to configure the service:

  • GOOGLE_APPLICATION_CREDENTIALS: Path to your service account credentials JSON file
  • GOOGLE_CREDENTIALS_CONFIG: JSON string containing service account credentials

Requirements

  • Python 3.11+
  • google-api-python-client>=2.0.0
  • google-auth-httplib2>=0.1.0
  • google-auth-oauthlib>=0.4.6
  • mcp>=1.0.0
  • pydantic>=1.8.0
  • python-dotenv>=0.19.0

Development

To set up the development environment:

  1. Clone the repository:
git clone https://github.com/yourusername/mcp-google-email.git
cd mcp-google-email
  1. Create and activate a virtual environment:
python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
  1. Install dependencies:
pip install -r requirements.txt

License

MIT License

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

README fetched from the repository 9 days ago. The original is authoritative.

Questions

About Gmail MCP

How do I install Gmail MCP?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Gmail MCP safe to use with an AI agent?

Its trust score is 37 out of 100 (low). It passes 3 of the 6 static security checks run so far; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Gmail MCP still maintained?

The last commit was a year ago and 1 open issues. That's long enough that you should check whether the maintainer is responding to issues before depending on it.