Gmail MCP Server
Allows AI assistants to interact with Gmail securely, providing capabilities such as fetching unread messages with metadata, drafting thread-aware replies, and managing email tasks via the Gmail API.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Gmail MCP Servercheck my unread emails"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Gmail MCP Server š§
A high-performance Model Context Protocol (MCP) server that enables AI assistants to interact with Gmail securely.
⨠Features
Smart Email Retrieval: Fetch unread messages with rich metadata.
Thread-Aware Drafting: Create replies that maintain conversation context.
Secure Authentication: Robust OAuth 2.0 implementation with token management.
Enterprise Ready: Structured for scalability and maintainability.
Related MCP server: Gmail AutoAuth MCP Server
šļø Architecture
System Data Flow
graph TD
User(["š¤ User"]) <-->|"Natural Language"| Claude(["š¤ Claude Desktop"])
subgraph "MCP Server (Local Machine)"
Claude <-->|"JSON-RPC (stdio)"| Main["src/main.py"]
Main -->|Dispatch| Handler["src/handlers.py"]
Handler -->|Call| Client["src/client.py"]
end
Client <-->|"HTTPS / OAuth 2.0"| Gmail(["āļø Google Gmail API"])
style User fill:#f9f,stroke:#333
style Claude fill:#e1f5fe,stroke:#01579b
style Gmail fill:#fce4ec,stroke:#880e4fThe project follows standard engineering practices:
MLI/
āāā src/
ā āāā main.py # Application Entry Point
ā āāā client.py # Gmail API Client
ā āāā handlers.py # Request Handlers
āāā config/ # Configuration & Credentials
āāā tests/ # Unit Tests
āāā requirements.txt # Dependenciesš Quick Start
1. Prerequisite
Python 3.8+
Google Cloud Project with Gmail API enabled
2. Installation
# Clone and setup environment
python -m venv .venv
.venv\Scripts\activate
# Install dependencies
pip install -r requirements.txt3. Configuration
Place your Google Cloud
credentials.jsoninconfig/.Copy the environment config:
copy .env.example .env
4. Claude Integration
Add to your Claude Desktop config (%APPDATA%\Claude\claude_desktop_config.json):
{
"mcpServers": {
"gmail": {
"command": "C:\\Path\\To\\MLI\\.venv\\Scripts\\python.exe",
"args": ["-m", "src.main"],
"cwd": "C:\\Path\\To\\MLI",
"env": {
"CREDENTIALS_PATH": "config/credentials.json",
"TOKEN_PATH": "config/token.json"
}
}
}
}š ļø Usage
Check Emails:
"Check my unread emails"
Draft Reply:
"Draft a reply to the email from [Name]"
š”ļø Security
Credentials are never committed to version control.
Tokens are stored locally in
config/.Communication happens directly between your machine and Google API.
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server connecting AI agents to 100+ apps (Gmail, Slack, Notion, GitHub) via one-click OAuth.
A MCP server for Gmail that lets you search, read, and draft emails and replies.
Email infrastructure for AI agents ā send, receive, search, and reply to email over MCP.
Shipmail MCP server for AI agent custom-domain email inboxes with REST API and webhooks.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAn MCP server that provides AI applications with a toolset for an Artificial Virtual Assistant (AVA) integrated with the Gmail API. It enables users to automate email management and personal tasks through secure Google OAuth authentication.1Apache 2.0
- AlicenseNot gradedqualityDmaintenanceAn MCP server enabling AI assistants to manage Gmail through natural language, including sending, reading, searching, labeling, and handling attachments with auto authentication.1MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server for Gmail that allows AI assistants to read, search, compose drafts, send emails, and manage labels with attachment support.MIT
- AlicenseNot gradedqualityCmaintenanceMCP server that lets AI assistants send, read, and manage Gmail through natural language, including email sending, inbox management, and template-based outreach.98 npmMIT