What is mail-mcp CLAUDE.md?

A set of coding instructions for a local service that connects Claude Cowork to Apple Mail accounts. The service searches and reads mail through Spotlight and mail files, and performs actions such as sending, replying, flagging, and moving messages through AppleScript.

Use it when developing or maintaining the mail service, including its TypeScript MCP server, mail search and parsing, AppleScript actions, input validation, and JSON-formatted tool responses.

It gives the coding agent the project’s architecture, file layout, conventions, and runtime permissions so changes fit the existing mail service.

How p-l-ta/mail-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to p-l-ta/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.

Copy the file

curl -O https://raw.githubusercontent.com/p-l-ta/mail-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/p-l-ta/mail-mcp

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/p-l-ta/mail-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/p-l-ta/mail-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/p-l-ta/mail-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/p-l-ta/mail-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/p-l-ta/mail-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/p-l-ta/mail-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 526 This file is loaded in full into every session.

When invoked 526 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00526	$0.00526
Opus 5.5	$0.00210	$0.00210
Sonnet 5.5	$0.00105	$0.00105
Haiku 4.5	$0.00053	$0.00053

Measured 2mo ago against content hash 9b3b6d53a57c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mail-mcp CLAUDE.md scanned grade A with 0 findings 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 2mo 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mail-mcp

Local MCP server that exposes Mail.app to Claude Cowork, giving Cowork Gmail-connector-like behavior across all mail accounts configured in Mail.app (iCloud, Exchange, IMAP, etc.).

Architecture

Search & read: Spotlight (mdfind) + direct .emlx parsing with mailparser. Fast, structured, no AppleScript text-scraping.
Actions (send, reply, flag, move): AppleScript via osascript, run from temp script files (never inline strings — escaping is a footgun).
Transport: stdio. Claude Desktop bridges this into Cowork via its SDK layer.

Layout

src/server.ts — MCP server entry, tool registration
src/tools/ — one file per tool (search, read, send, reply, flags, etc.)
src/lib/applescript.ts — temp-file runner
src/lib/emlx.ts — Apple's emlx wrapper around RFC-822
src/lib/spotlight.ts — mdfind query builder
prototype.js — original single-file sketch, reference only

Conventions

TypeScript, ES modules, Node 20+
Zod schemas for every tool input
Tool outputs are JSON strings inside { type: "text" } content blocks
AppleScript is generated as full scripts written to tmp files, then executed with execFile("osascript", [path]). Never use osascript -e with template strings.
Every tool has a vitest unit test with mocked execFile / mdfind / fs

Permissions required at runtime

Automation → Mail.app (System Settings → Privacy & Security → Automation)
Full Disk Access for the node binary (to read ~/Library/Mail/)

Testing

npm test — vitest
npm run dev — tsx watch on src/server.ts (manual MCP testing via inspector)
Use npx @modelcontextprotocol/inspector node dist/server.js for interactive testing

Out of scope

Gmail (Cowork already has a connector for that)
Remote/HTTP transport (this is a local stdio server bridged through Desktop)
Rendering HTML email bodies (return text/plain; expose HTML availability flag only)

Node version

This project requires Node 20+ (see .nvmrc). If using fnm: fnm use.

Read the full file on GitHub · 54 lines

Changes

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.

2mo ago First seen · 54 lines · 526 tokens per session scan A 9b3b6d53a57c

Subscribe to this mod's changes

mail-mcp CLAUDE.md is an instructions file published in the GitHub repository p-l-ta/mail-mcp (1 stars, last pushed 3mo ago), licensed MIT. It adds 526 tokens to every session, about $0.0021 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Backend and APIs

mail-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mail-mcp CLAUDE.mdp-l-ta/mail-mcp	Instructions file	1	3mo ago	MIT	A	526	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

mail-mcp: Instructions file for Claude Code