An MCP server that gives AI assistants full access to Apple Mail -- read, search, compose, organize, and analyze emails via natural language. Built with FastMCP.
Apple Mail is an MCP project maintained in the patrickfreyer/apple-mail-mcp repository. The maintainer describes its purpose as “An MCP server that gives AI assistants full access to Apple Mail -- read, search, compose, organize, and analyze emails via natural language. Built with…”. Read the project documentation for the complete scope.
The documented pypi package is mcp-apple-mail. The configuration below comes from the maintainer’s example; adapt its paths and account values to your environment.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| get_inbox_overview | Dashboard with unread counts, folders, and recent emails |
| list_inbox_emails | List emails with account/read-status filtering and optional content preview |
| get_mailbox_unread_counts | Unread counts per mailbox or per-account summary |
| list_accounts | List all configured Mail accounts |
| search_emails | Unified search — subject, sender, body text, dates, attachments, flag status/color, cross-account |
| get_email_thread | Conversation thread view |
| list_mailboxes | Folder hierarchy with message counts |
| create_mailbox | Create new mailboxes (supports nested paths) |
| move_email | Move/archive emails with filters (subject, sender, date, read status, dry-run) |
| update_email_status | Mark read/unread, flag/unflag (optional flag color) — by filters or message IDs |
| manage_trash | Soft delete, permanent delete, empty trash (with dry-run) |
| compose_email | Send new emails (plain text or HTML body) |
| reply_to_email | Reply or reply-all with optional HTML body |
| forward_email | Forward with optional message, CC/BCC |
| manage_drafts | Create, list, send, and delete drafts |
| create_rich_email_draft | Build a rich HTML .eml draft, open it in Mail, and optionally save it to Drafts |
| list_email_attachments | List attachments with names and sizes |
| save_email_attachment | Save attachments to disk |
| get_awaiting_reply | Find sent emails that haven't received a reply |
| get_needs_response | Identify emails that likely need your response |
| get_top_senders | Analyse most frequent senders by count or domain |
| get_statistics | Email analytics (volume, top senders, read ratios) |
| export_emails | Export single emails or mailboxes to TXT/HTML |
| inbox_dashboard | Interactive UI dashboard (requires mcp-ui-server) |
{
"mcpServers": {
"apple-mail": {
"command": "uvx",
"args": [
"mcp-apple-mail"
]
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
Your assistant inside the workspace — read channels, search history, post messages and tame the noise.
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Inbox intelligence — search, read, draft and send Gmail through your assistant with OAuth auto-setup.
Read and write Jira, Confluence, Bitbucket, JSM and Compass from your AI client — with your own permissions.
Read and send Telegram messages through your assistant — chats, channels and history via the client API.
Enables Discord bot integration with Model Context Protocol (MCP) compatible applications like Claude Desktop.