FastMail MCP Server
An MCP server that integrates with FastMail's JMAP API to manage mailboxes, search for emails, and send messages. It enables users to interact with their FastMail account for tasks like reading email content and managing folders through natural language.
README
FastMail MCP Server
A Model Context Protocol (MCP) server for integrating with FastMail's JMAP API. This server provides tools for reading emails, searching, managing folders, and sending emails through FastMail.
š Features
- š Mailbox Management: List and find mailboxes/folders
- š§ Email Reading: Get emails from specific folders with previews
- š Advanced Search: Search by keyword, sender, subject, date range, attachments
- š¤ Email Sending: Send emails with CC/BCC support
- šÆ Folder Targeting: Search within specific folders
- ā” Fast Performance: Uses FastMail's modern JMAP protocol
š Prerequisites
- Python 3.8+
- FastMail account with API access
- API token from FastMail (Settings ā Privacy & Security ā Integrations)
š Installation
-
Clone the repository:
git clone <your-repo-url> cd fastmail-mcp-server -
Install dependencies:
pip install -r requirements.txt -
Get your FastMail API token:
- Log into FastMail
- Go to Settings ā Privacy & Security ā Integrations
- Create a new API token
- Copy the token (starts with
fmu1-)
š Usage
Running the Server
python fastmail_mcp_server.py
The server will start and listen for MCP commands via stdio.
Configuration
First, configure your FastMail credentials:
{
"tool": "configure_fastmail",
"arguments": {
"apiToken": "fmu1-your-token-here"
}
}
Available Tools
š configure_fastmail
Set up your FastMail API credentials.
š list_mailboxes
List all mailboxes with their names, roles, and email counts.
{
"tool": "list_mailboxes",
"arguments": {
"role": "inbox" // Optional: filter by role
}
}
š find_mailbox
Find a specific mailbox by name or role.
{
"tool": "find_mailbox",
"arguments": {
"name": "Work", // Partial matching supported
"role": "sent" // Or search by role
}
}
š§ get_emails
Get emails from a specific mailbox.
{
"tool": "get_emails",
"arguments": {
"mailboxId": "mailbox-id-here", // From list_mailboxes
"mailboxName": "Inbox", // Alternative to mailboxId
"limit": 20, // Max emails to fetch
"includeBody": false // Include full email body
}
}
š search_emails
Search emails with advanced filtering.
{
"tool": "search_emails",
"arguments": {
"keyword": "project update", // Text search
"from_email": "boss@company.com", // From specific sender
"subject": "meeting", // Subject contains
"mailboxId": "inbox-id", // Search within folder
"hasAttachment": true, // Has attachments
"after": "2024-01-01", // Date range
"before": "2024-12-31",
"limit": 50,
"includeBody": false
}
}
š get_email_body
Get the full body content of a specific email.
{
"tool": "get_email_body",
"arguments": {
"emailId": "email-id-here",
"format": "text" // "text", "html", or "both"
}
}
š¤ send_email
Send an email through FastMail.
{
"tool": "send_email",
"arguments": {
"to": ["recipient@example.com"],
"cc": ["cc@example.com"], // Optional
"bcc": ["bcc@example.com"], // Optional
"subject": "Hello from MCP!",
"body": "This is the email body.",
"isHtml": false // Set to true for HTML emails
}
}
š§ Integration with MCP Clients
Claude Desktop
Add to your Claude Desktop config:
{
"mcpServers": {
"fastmail": {
"command": "python",
"args": ["/path/to/fastmail_mcp_server.py"]
}
}
}
Other MCP Clients
This server follows the standard MCP protocol and should work with any MCP-compatible client.
š Project Structure
fastmail-mcp-server/
āāā fastmail_mcp_server.py # Main server implementation
āāā requirements.txt # Python dependencies
āāā pyproject.toml # Package configuration
āāā README.md # This file
āāā examples/ # Example usage scripts
āāā test_server.py # Test script
š Security Notes
- API Token Security: Never commit your API token to version control
- Permissions: The API token has access to your entire FastMail account
- Network: All communication uses HTTPS with FastMail's secure APIs
š Troubleshooting
Common Issues
- Authentication Error: Verify your API token is correct and has proper permissions
- Connection Error: Check your internet connection and FastMail service status
- Missing Emails: Ensure you're searching in the correct mailbox
Debug Mode
Enable debug logging by setting environment variable:
export MCP_DEBUG=1
python fastmail_mcp_server.py
š¤ Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Submit a pull request
š License
MIT License - see LICENSE file for details.
š Acknowledgments
- FastMail for their excellent JMAP API
- Model Context Protocol by Anthropic
- JMAP Specification by the IETF
š Additional Resources
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.