Skip to main content

Gmail MCP Server

A Model Context Protocol (MCP) server that provides Gmail integration capabilities through a clean, async API.

Features

  • 🔍 Search emails with Gmail's powerful search syntax
  • 📧 Send emails with support for CC/BCC
  • 📋 Get recent emails from inbox
  • 📄 Get detailed email content including full body
  • 🏷️ List Gmail labels (system and custom)
  • 📁 Get emails by label (INBOX, STARRED, etc.)
  • 💚 Health check to verify server and API connectivity
  • ⏱️ Timeout protection for all API calls
  • 🔄 Token refresh capability (requires client credentials)

Quick Start

1. Install Dependencies

pip install fastmcp requests pydantic

2. Set up Gmail API Credentials

  1. Go to Google Cloud Console
  2. Create a new project or select existing one
  3. Enable the Gmail API
  4. Create OAuth 2.0 credentials
  5. Download the credentials file

3. Get Access and Refresh Tokens

You'll need to obtain OAuth 2.0 tokens for Gmail API access. You can use the Google OAuth 2.0 playground or create a simple script to get these tokens.

4. Run the Server

python trial1.py --access-token YOUR_ACCESS_TOKEN --refresh-token YOUR_REFRESH_TOKEN

5. Test the Server

python test_server.py

Available Tools

search_emails

Search Gmail using Gmail's search syntax.

Input:

{
  "params": {
    "query": "from:example@gmail.com",
    "max_results": 10,
    "include_body": false
  }
}

Examples:

  • after:2025/06/17 - Emails after specific date
  • from:example@gmail.com - Emails from specific sender
  • subject:meeting - Emails with specific subject
  • is:unread - Unread emails
  • has:attachment - Emails with attachments

get_recent_emails

Get the most recent emails from inbox.

Input:

{
  "max_results": 10
}

get_email_details

Get complete details of a specific email including full body content.

Input:

{
  "params": {
    "message_id": "18c1234567890abcdef"
  }
}

send_email

Send an email via Gmail.

Input:

{
  "params": {
    "to": "recipient@email.com",
    "subject": "Email Subject",
    "body": "Email content",
    "cc": "cc@email.com",
    "bcc": "bcc@email.com"
  }
}

list_gmail_labels

List all Gmail labels including system and user-created labels.

Input:

{}

get_emails_by_label

Fetch emails that belong to a specific Gmail label.

Input:

{
  "label_id": "INBOX",
  "max_results": 10
}

health_check

Check the health and connectivity of the Gmail MCP server.

Input:

{}

Configuration

Environment Variables

You can set these environment variables instead of passing tokens as arguments:

  • GMAIL_ACCESS_TOKEN - Your Gmail API access token
  • GMAIL_REFRESH_TOKEN - Your Gmail API refresh token

Server Settings

The server is configured with:

  • Port: 8010
  • Log level: INFO
  • Cache expiration: 60 seconds
  • Gmail API timeout: 30 seconds

Error Handling

The server includes comprehensive error handling:

  • Timeout protection for all API calls
  • Graceful handling of expired tokens
  • Detailed error messages for debugging
  • Fallback responses for failed operations

Security Considerations

  • Never commit tokens to version control
  • Use environment variables for sensitive data
  • Consider implementing token refresh for long-running sessions
  • Validate all input parameters

Troubleshooting

Common Issues

  1. "Invalid credentials" error

    • Check that your access token is valid and not expired
    • Verify your refresh token is correct
  2. "Permission denied" error

    • Ensure your Gmail API credentials have the necessary scopes
    • Check that the Gmail API is enabled in your Google Cloud project
  3. "Timeout" errors

    • The server has a 30-second timeout for Gmail API calls
    • For large email searches, try reducing max_results

Testing

Run the test script to verify your setup:

python test_server.py

Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Add tests if applicable
  5. Submit a pull request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Metadata

Release files for gmail-mcp-server-ansh 1.0.5

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for gmail-mcp-server-ansh 1.0.5
File Size Uploaded Provenance
gmail_mcp_server_ansh-1.0.5.tar.gz 14.6 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for gmail-mcp-server-ansh 1.0.5
File Interpreter ABI Platform
gmail_mcp_server_ansh-1.0.5-py3-none-any.whl Python 3 none any Details

Total release size: 30.6 kB

Release files / gmail_mcp_server_ansh-1.0.5.tar.gz

Download URL gmail_mcp_server_ansh-1.0.5.tar.gz
Size 14.6 kB
Tags Source
SHA-256 checksum
How to use checksums
1a41b68c2ecd6fc3caf91dc8620f78d7d018c5ed081f445712ded95cde58395b
BLAKE2b-256 checksum
How to use checksums
9cf04fc79180c6ff081e42bb840204ca4c2cf232c5a60b718f340516bf9462c4
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.10.12

Release files / gmail_mcp_server_ansh-1.0.5-py3-none-any.whl

Download URL gmail_mcp_server_ansh-1.0.5-py3-none-any.whl
Size 16.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
c76d57c7096169ea5758a15773a4d0a83a2abdef56ec031e311a897a5cea0f77
BLAKE2b-256 checksum
How to use checksums
3ffde3f3478d0261d49bb61957eecb721293de207f26bf3298c3767f7d22adaf
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.10.12

Security for gmail-mcp-server-ansh 1.0.5

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page