Gmail MCP Server
Provides access to Gmail functionalities including listing unread emails, searching via query syntax, and managing messages through archiving or marking as read. It enables MCP clients to securely interact with and organize email data using the Gmail API.
README
Gmail MCP Server
A Model Context Protocol (MCP) server that provides Gmail access for Claude Code and other MCP clients. Built with FastMCP.
Features
- list_unread - List unread emails from inbox
- search - Search emails using Gmail query syntax
- archive - Archive emails (removes from inbox)
- mark_as_read - Mark emails as read without archiving
- get_labels - Get all Gmail labels
Installation
No local installation required! Run directly from GitHub using uvx:
uvx --from git+https://github.com/fred-drake/gmail-mcp gmail-mcp
Setup
1. Create Google Cloud OAuth Credentials
-
Go to Google Cloud Console
-
Create a new project or select an existing one:
- Click the project dropdown at the top of the page
- Click "New Project", give it a name, and create it
- Make sure your new project is selected
-
Enable the Gmail API:
- Navigate to "APIs & Services" > "Library"
- Search for "Gmail API" and click on it
- Click "Enable"
-
Configure the OAuth consent screen (required before creating credentials):
- Go to "APIs & Services" > "OAuth consent screen"
- Select "External" as the user type and click "Create"
- Fill in the required fields:
- App name: Choose any name (e.g., "Gmail MCP")
- User support email: Select your email
- Developer contact email: Enter your email
- Click "Save and Continue"
- On the "Scopes" page, click "Save and Continue" (no changes needed)
- On the "Test users" page:
- Click "Add Users"
- Enter the Gmail address you want to access (this is critical!)
- Click "Add" then "Save and Continue"
- Click "Back to Dashboard"
-
Create OAuth credentials:
- Go to "APIs & Services" > "Credentials"
- Click "Create Credentials" > "OAuth client ID"
- Choose "Desktop app" as the application type
- Give it a name (e.g., "Gmail MCP Desktop")
- Click "Create"
- Click "Download JSON" to save the credentials file
- Store this file securely - you'll need the path for configuration
2. Set Environment Variables
Set the path to your OAuth credentials file:
export GMAIL_MCP_CREDENTIALS_PATH="/path/to/your/credentials.json"
Optionally, customize the token cache location (default: ~/.config/gmail-mcp/token.json):
export GMAIL_MCP_TOKEN_PATH="/custom/path/token.json"
3. Run OAuth Setup
Run the interactive setup to authenticate:
uvx --from git+https://github.com/fred-drake/gmail-mcp gmail-mcp --setup
This will open a browser window for Google OAuth authentication. After authorizing, the token will be cached for future use.
MCP Client Configuration
Claude Code
Add to your Claude Code MCP settings:
{
"mcpServers": {
"gmail": {
"command": "uvx",
"args": ["--from", "git+https://github.com/fred-drake/gmail-mcp", "gmail-mcp"],
"env": {
"GMAIL_MCP_CREDENTIALS_PATH": "/path/to/your/credentials.json"
}
}
}
}
With Custom Token Path
{
"mcpServers": {
"gmail": {
"command": "uvx",
"args": ["--from", "git+https://github.com/fred-drake/gmail-mcp", "gmail-mcp"],
"env": {
"GMAIL_MCP_CREDENTIALS_PATH": "/path/to/your/credentials.json",
"GMAIL_MCP_TOKEN_PATH": "/custom/path/token.json"
}
}
}
}
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
GMAIL_MCP_CREDENTIALS_PATH |
Yes | - | Path to OAuth credentials JSON |
GMAIL_MCP_TOKEN_PATH |
No | ~/.config/gmail-mcp/token.json |
Path to token cache file |
Tool Reference
list_unread
List unread emails from inbox.
Parameters:
max_results(int, optional): Maximum emails to return (1-100). Default: 20.
Returns: List of email objects with id, from, subject, date, snippet, labels, body_preview.
search
Search emails using Gmail query syntax.
Parameters:
query(str): Gmail search query (e.g., "from:user@example.com is:unread")max_results(int, optional): Maximum results (1-100). Default: 20.
Returns: List of matching email objects.
Example queries:
from:notifications@github.com- Emails from GitHubis:unread newer_than:1d- Unread emails from last 24 hourssubject:invoice- Emails with "invoice" in subjecthas:attachment larger:5M- Emails with attachments over 5MB
archive
Archive emails by removing INBOX and UNREAD labels.
Parameters:
message_ids(list[str]): List of message IDs to archive.
Returns: Dict with archived_count, failed_count, and details.
mark_as_read
Mark emails as read without archiving.
Parameters:
message_ids(list[str]): List of message IDs to mark as read.
Returns: Dict with marked_count, failed_count, and details.
get_labels
Get all Gmail labels for the authenticated user.
Returns: List of label objects with id, name, type, and message counts.
Development
Prerequisites
- Python 3.13+
- Nix (optional, for reproducible environment)
Setup with Nix
cd gmail-mcp
nix develop
Setup with pip
cd gmail-mcp
pip install -e ".[dev]"
Running Tests
pytest
Linting
ruff check .
ruff format .
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.