mcp_mail CLAUDE.md

mcp_mail CLAUDE.md is an instructions file for coding agents from jleechanorg/mcp_mail. It costs 3,799 tokens per session, scanned B, original, MIT.

Instruction notes for running and testing mcp_agent_mail, a server for agent communication. They describe starting it from its Python package or local source and recommend testing real integrations.

In plain words
What is it for?
Use them when setting up mcp_agent_mail, developing it from source, or testing integrations such as Slack.
Why use it?
They clarify how the server should be started and help keep development checks focused on the parts that changed.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/jleechanorg/mcp_mail/claude-md
Clone the repo
git clone --depth 1 https://github.com/jleechanorg/mcp_mail

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.

agentmods badge for mcp_mail CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jleechanorg/mcp_mail/claude-md.svg)](https://agentmods.dev/instructions/jleechanorg/mcp_mail/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jleechanorg/mcp_mail/claude-md"><img src="https://agentmods.dev/badge/instructions/jleechanorg/mcp_mail/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,799 This file is loaded in full into every session.
When invoked 3,799 The same file — it is already loaded in full.
Security scan B 2 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.03799 $0.03799
Opus 5 $0.01899 $0.01899
Sonnet 5 $0.00760 $0.00760
Haiku 4.5 $0.00380 $0.00380

Measured 5d ago against content hash 178cbfdbe862, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

mcp_mail CLAUDE.md scanned grade B with 2 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 5d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

chmod 600 ~/.pypirc

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -H "Authorization: Bearer $GITHUB_TOKEN" https://api.github.com/repos/owner/repo
CLAUDE.md · 431 lines

How it starts

The opening of the file, as written. The whole thing — 431 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Agent Notes

Claude Code (or Claude Desktop) must assume the MCP Agent Mail server is already running in the background before it connects. Always start/refresh the server with a background bash -lc call so you capture the PID and tee logs to a safe location.

Proactive defaults: run ./scripts/ensure_git_hooks.sh once per clone/session (or after git ops) to enforce hooks and force core.hooksPath=.githooks, then run targeted tests for the surfaces you touch (e.g., Slack integration → uv run pytest tests/integration/test_slack_mcp_mail_integration.py) without waiting for instructions. Hooks include Ruff/ty/Bandit on commit.

Use the published PyPI package for production use:

bash -lc "cd /Users/jleechan/mcp_agent_mail && ./scripts/run_server_pypi.sh >/tmp/mcp_agent_mail_server.log 2>&1 & echo \$!"

This installs mcp_mail from PyPI in an isolated environment and runs the server.

Running from Local Source (Development)

For development with local code changes:

bash -lc "cd /Users/jleechan/mcp_agent_mail && ./scripts/run_server_with_token.sh >/tmp/mcp_agent_mail_server.log 2>&1 & echo \$!"

Testing Philosophy — Real Over Fake

Always prefer real end-to-end tests. Mocks and stubs are only acceptable for isolated unit tests.

For any suite or artifact under testing_*/:

  • No mocks
  • No monkeypatching
  • No stubbed external service behavior (Slack, GitHub, databases, etc.)
  • No direct registry/state injection
  • No modifying the system under test through internal hooks, direct state injection, or other non-public control paths while claiming verification

testing_*/ directories may only trigger the system from the outside and observe evidence. Public/API-driven setup and teardown (e.g., using documented endpoints, test accounts, or CLI commands) is permitted. If a test needs simulated internals, it belongs in tests/ (or equivalent unit test directory) and must not be described as end-to-end proof.

Read the full file on GitHub · 431 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.

  1. 5d ago First seen · 431 lines · 3,799 tokens per session scan B 178cbfdbe862

Subscribe to this mod's changes

mcp_mail CLAUDE.md is an instructions file published in the GitHub repository jleechanorg/mcp_mail (11 stars, last pushed 19d ago), licensed MIT. It adds 3,799 tokens to every session, about $0.0190 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens