Apple MailSAFE
MCP server giving AI assistants full access to Apple Mail - read, search, compose, organize & analyze emails via natural language
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://opensource.org/licenses/MIT) [](https://pypi.org/project/mcp-apple-mail/) [](https://www.python.org/downloads/) [](https://modelcontextprotocol.io) [](https://github.com/patrickfreyer/apple-mail-mcp/stargazers)
Star History
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.
Quick Install
Prerequisites: macOS with Apple Mail configured, Python 3.10+
Claude Code Plugin (Recommended)
Two commands — gets you the MCP server, /email-management slash command, and the Email Management Expert skill:
claude plugin marketplace add patrickfreyer/apple-mail-mcp claude plugin install apple-mail@apple-mail-mcp
Then restart Claude Code.
Other Install Methods
uvx (zero install, MCP server only)
claude mcp add apple-mail -- uvx mcp-apple-mail
Or for Claude Desktop (`~/Library/Application Support/Claude/claude_deskt
e8f5e4d5232aOBSERVED · 2026-10-06Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add mcp-apple-mail -- None mcp-apple-mail==3.2.0
Exposed tools (1)
1 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
get_email_source | read | Return the raw RFC 822 source of a single message. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (1)
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](https://github.com/jlowin/fastmcp).
Gates applied: no_behavioural_pass.
e8f5e4d5232afull audit observations/trust-audit/mcp-server/patrickfreyer__apple-mail-1.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-06 | e8f5e4d5232a | SAFE | B | 89 | first audit |
Questions
What is the Apple Mail MCP server?
MCP server giving AI assistants full access to Apple Mail - read, search, compose, organize & analyze emails via natural language
What tools does Apple Mail expose?
1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Apple Mail safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Apple Mail need?
No credential environment variables were found in its source, so it appears to need none.
How does Apple Mail run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as mcp-apple-mail.
How current is this page?
The grade is for one exact copy of the source (e8f5e4d5232a), read on 2026-10-06. The repository is watched and re-audited when it changes.