Gmail

Provides Gmail access via MCP to manage, read, search, and organize emails using Claude.
  • python

0

GitHub Stars

python

Language

6 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "mcp-mirror-samarth2001_gmail-mcp": {
      "command": "python",
      "args": [
        "/absolute/path/to/gmail-mcp-server/gmail_server.py"
      ],
      "env": {
        "DEBUG": "false",
        "MCP_PORT": "3000",
        "GMAIL_TOKEN_PATH": "TOKEN_PATH_PLACEHOLDER",
        "GOOGLE_CLIENT_ID": "YOUR_CLIENT_ID",
        "GOOGLE_CLIENT_SECRET": "YOUR_CLIENT_SECRET",
        "GMAIL_CREDENTIALS_PATH": "CREDENTIALS_PATH_PLACEHOLDER"
      }
    }
  }
}

You can run the Gmail MCP Server locally to let Claude interact with Gmail through natural language. It exposes a rich set of email-management capabilities, supports secure OAuth authentication, and can be run in standard or SSE (Server-Sent Events) modes for different integration patterns. This guide walks you through installing, configuring, and using the server end to end.

How to use

Start by launching the Gmail MCP Server on your machine. You will run a Python process that starts an MCP endpoint locally. The server authenticates with Google using OAuth, reads your Gmail data, and exposes a set of tools Claude can invoke to send, read, search, label, and manage emails. Use the standard local run to interact via the default MCP transport, or run in SSE mode to expose an HTTP-based endpoint for remote clients.

How to install

Prerequisites: Install Python 3.8 or higher and ensure you have a Google Cloud project with Gmail API enabled and OAuth credentials.

Step 1. Create a Python virtual environment and activate it.

python -m venv venv

# On Windows
venv\Scripts\activate

# On macOS/Linux
source venv/bin/activate

Step 2. Install dependencies.

pip install -r requirements.txt

Step 3. Set up Google Cloud and OAuth credentials. Create a Google Cloud project, enable the Gmail API, configure OAuth consent, create Desktop OAuth credentials, and download credentials.json to the project root.

First run and authentication

Run the server once to authenticate with Google. A browser window will prompt you to sign in. After you authorize access, a token.json file is created for subsequent runs.

python gmail_server.py

Configure Claude Desktop

Add the Gmail MCP server to Claude Desktop so it can communicate with your local MCP endpoint. Use the absolute path to the server script in your setup.

{
  "mcpServers": {
    "gmail": {
      "command": "python",
      "args": [
        "/absolute/path/to/gmail-mcp-server/gmail_server.py"
      ]
    }
  }
}

Environment and transport notes

You can customize how the server runs using environment variables and by selecting the transport mode. SSE mode exposes an HTTP-based endpoint for integration, while the default mode uses the local transport.

Additional configuration and runtime options

To run in SSE mode on a specific port, start the server with the SSE flag and port number.

python gmail_server.py --sse 3000

Available tools

send_email

Send basic emails with text or HTML content

send_email_with_attachment

Send emails with file attachments

read_email

Read the content of a specific email by ID

search_emails

Search emails using Gmail query syntax

get_email_labels

List all Gmail labels/folders

create_email_label

Create a new Gmail label

update_email_draft

Update an existing draft email

list_email_drafts

List available drafts

send_draft

Send an existing draft

batch_apply_label

Apply a label to multiple emails

get_email_profile

Get Gmail profile information

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational