Borrowing it
Nothing to install: this file belongs to friisconsult/imap-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/friisconsult/imap-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/friisconsult/imap-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/friisconsult/imap-mcp/claude-md)<a href="https://agentmods.dev/instructions/friisconsult/imap-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/friisconsult/imap-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 | $0.01158 | $0.01158 |
| Opus 5 | $0.00579 | $0.00579 |
| Sonnet 5 | $0.00232 | $0.00232 |
| Haiku 4.5 | $0.00116 | $0.00116 |
Grade A, and why
imap-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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Overview
imap-mcp is a single-file Python MCP server (server.py, FastMCP over stdio) that gives Claude Desktop/Cowork/Code access to plain IMAP/SMTP mailboxes — the accounts not covered by the official Gmail/M365 connectors. There is no package structure: server.py holds all tools, test_server.py the tests, install.py the Claude Desktop registration.
Commands
bash setup.sh # create .venv, install deps, register in Claude Desktop (idempotent)
.venv/bin/python server.py --check # validate accounts.json + password resolution without starting the server
.venv/bin/python server.py --set-password "<account>" # store a password in the OS keychain
.venv/bin/python test_server.py # run tests (offline — no mail server, no framework, plain asserts)
On Windows use .\setup.ps1 and .venv\Scripts\python.exe. There is no pytest/lint setup; the test file is a script that prints per-check status and ALL CHECKS PASSED.
Configuration lives in accounts.json (gitignored, plain-text credentials — never commit or print it). accounts.example.json is the template; install.py copies it on first setup and registers the server as imap-mail in Claude Desktop's config.
Architecture: config-level safety gating
The central design decision is that all guardrails live in accounts.json, not in prompts or tool descriptions, so they hold under prompt injection from mail content. Every tool falls into one of three tiers, and any new tool must be gated the same way:
- Read tools (search, get, list, download) — always allowed, but must connect read-only and fetch with
mark_seen=Falseso nothing is even marked read as a side effect. - Write tools (move, trash, create folder, mark, create draft) — must call
_require_writes(account)first, which raisesPermissionErrorunless the account has"allow_writes": true. Deletion does not exist:trash_messagesonly moves to the account'strash_folder(defaultTrash); never add expunge/permanent delete.create_draftonly APPENDs to thedrafts_folder(defaultDrafts) — it composes but can never send, which is why it is a write tool, not a send tool. - Send (
forward_messageonly) — must call_require_send(account, to), which enforces theallow_send_tofnmatch whitelist and requires ansmtpblock. There is deliberately no send-new-mail tool.
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.
- 7d ago First seen · 46 lines · 1,158 tokens per session scan A 739d73c314d8
imap-mcp CLAUDE.md is an instructions file published in the GitHub repository friisconsult/imap-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,158 tokens to every session, about $0.0058 per session on Opus 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.
Other instructions, from other repositories
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).
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.
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.
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).
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.