Borrowing it
Nothing to install: this file belongs to sweetrb/apple-mail-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sweetrb/apple-mail-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/sweetrb/apple-mail-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/sweetrb/apple-mail-mcp/claude-md)<a href="https://agentmods.dev/instructions/sweetrb/apple-mail-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sweetrb/apple-mail-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.05218 | $0.05218 |
| Opus 5 | $0.02609 | $0.02609 |
| Sonnet 5 | $0.01044 | $0.01044 |
| Haiku 4.5 | $0.00522 | $0.00522 |
Grade A, and why
apple-mail-mcp CLAUDE.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
Prior to v1.4.0, `reply-to-message` and `forward-message` would send replies/forwards with **empty body text** when the MCP server was running as a background process (e.g., spawned via `execSync` from a Node.js MCP serv How it starts
The opening of the file, as written. The whole thing — 437 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - Apple Mail MCP Server
This file provides guidance for AI agents (Claude, etc.) when using this MCP server.
Overview
This MCP server enables AI assistants to interact with Apple Mail on macOS via AppleScript. All operations are local - no data leaves the user's machine.
Configuring IMAP / SMTP (when a user asks to set it up)
The AppleScript backend needs no config. The opt-in IMAP (fast search/counts on
large mailboxes) and SMTP (clean sending, no macOS 15+ <blockquote> wrapping)
backends are configured via non-secret APPLE_MAIL_MCP_* settings — supplied in an
env block or, for hosts that strip env (e.g. Claude Desktop), a
config.json at ~/Library/Application Support/apple-mail-mcp/config.json (loaded
into the environment at startup) — with passwords kept in the macOS Keychain.
Don't reverse-engineer it: the full walkthrough is docs/IMAP-SETUP.md
(app passwords, Keychain, both config methods, multi-account, SMTP, headless/SSH
Keychain gotchas). Verify with the doctor tool.
Critical: Backslash Escaping
When sending content with backslashes to any tool, you MUST escape them.
The MCP protocol uses JSON for parameters. In JSON, \ is an escape character. To include a literal backslash:
| You want | Send in JSON parameter |
|---|---|
\ |
\\ |
\\ |
\\\\ |
Mobile\ Documents |
Mobile\\ Documents |
Why This Matters
If you send a single backslash without escaping:
- The JSON parser interprets
\as an escape sequence - Invalid sequences like
\(backslash-space) cause silent failures - The email send/draft may fail with no clear error
Examples
Correct - shell path with an escaped space:
body: "Run: cp ~/Library/Mobile\\ Documents/report.pdf ~/Desktop/"
→ arrives as: Run: cp ~/Library/Mobile\ Documents/report.pdf ~/Desktop/
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago Changed · +6 lines · +147 tokens per session da639c1a9ddf
- 8d ago First seen · 431 lines · 5,071 tokens per session scan A d11d6ac5dae6
apple-mail-mcp CLAUDE.md is an instructions file published in the GitHub repository sweetrb/apple-mail-mcp (69 stars, last pushed yesterday), licensed MIT. It adds 5,218 tokens to every session, about $0.0261 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.