Advertise
MCP.so
Sign In

Gmail MCP Server

@Imsharad

Repository

Basic information

Category

Communication

Transports

stdio

Author

Imsharad

About Gmail MCP Server

A Gmail Model Context Protocol server for seamless integration with AI assistants

#gmail#mcp#server#ai-assistant

Gmail MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "gmail": {
      "command": "python",
      "args": [
        "-m",
        "src.server"
      ],
      "cwd": "/path/to/gmail-mcp-server"
    }
  }
}

Gmail MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Gmail MCP Server?

The Gmail MCP Server provides access to Gmail functionality through the Model Context Protocol, allowing LLMs like Claude to interact with your email. It is designed for developers and AI assistants that need to read, search, send, and reply to emails programmatically.

How to use Gmail MCP Server?

Set up a Python virtual environment, install dependencies, enable the Gmail API in Google Cloud Console, and download OAuth 2.0 credentials as credentials.json. Run the server with python -m src.server; the first launch opens a browser for authentication. Afterwards, configure Claude Desktop by adding the server to claude_desktop_config.json with the command python -m src.server and the project directory as the working directory.

Key features of Gmail MCP Server

  • List emails from your inbox
  • Search for specific emails
  • Read email content
  • Send new emails
  • Reply to existing emails

Use cases of Gmail MCP Server

  • An AI assistant reads and summarizes unread emails on demand
  • A Claude‑powered tool searches for important messages by keyword
  • Automated reply workflows triggered by LLM prompts
  • Drafting and sending emails without leaving the chat interface

Frequently asked questions

1

What is the Gmail MCP Server?

It is an MCP server that gives LLMs like Claude the ability to interact with Gmail – listing, searching, reading, sending, and replying to emails.

2

How do I set up authentication?

Create a Google Cloud project, enable the Gmail API, and generate OAuth 2.0 credentials (desktop application type). Download the credentials as `credentials.json` into the project root. On first run, the server opens a browser for authorization and saves the tokens to `token.json`.

3

What security considerations are there?

Keep your `credentials.json` and `token.json` files secure and never commit them to version control. If you suspect compromise, revoke the credentials in the Google Cloud Console and generate new ones.

4

What are the Gmail API rate limits?

The Gmail API allows up to 1,000,000,000 quota units per day, with each API method consuming different amounts. For details, refer to Google’s Gmail API Quotas documentation.

5

How do I configure Claude Desktop to use this server?

Add the server to your `claude_desktop_config.json` with the command `python -m src.server` and set the working directory to the project path.

Comments

More Communication MCP servers

Agent Inbox

Agent Inbox

Give your agent an inbox. Its own address on email, Slack and Telegram. A product of Novu

SendRaven

CommonNinja

SendRaven is email infrastructure for AI agents. Send, read replies as threads, run campaigns and automations, with limits on the API key.

1

ARVX

Centric AI, Inc.

Email for long-term client relationships: ARVX reads each person first and remembers every pair.

Odile Direct by Odile Labs

Odile Labs

Odile Direct: AI agents reach a real business by its phone number. Look a business up free, leave a message, check open times or book a slot, then read the owner's reply in the same thread. 50 free tasks a month per agen

Canarics

Canarics

AI call analysis and voice agents for sales teams. This MCP server lets a team's own AI assistant read minute usage, agents, call summaries and daily stats, look up caller history, schedule consent-gated AI callbacks, an

Advertise