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.
npx agentmods add instructions/wh1isper/mcp-email-server/agents-mdgit clone --depth 1 https://github.com/Wh1isper/mcp-email-serverWrote 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/wh1isper/mcp-email-server/agents-md)<a href="https://agentmods.dev/instructions/wh1isper/mcp-email-server/agents-md"><img src="https://agentmods.dev/badge/instructions/wh1isper/mcp-email-server/agents-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 | $0.02504 | $0.02504 |
| Opus 5 | $0.01252 | $0.01252 |
| Sonnet 5 | $0.00501 | $0.00501 |
| Haiku 4.5 | $0.00250 | $0.00250 |
Grade A, and why
mcp-email-server AGENTS.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 6d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Overview
mcp-email-server is a Python MCP server that connects MCP clients to email
accounts through IMAP and SMTP.
Canonical repository:
- HTTPS:
https://github.com/Wh1isper/mcp-email-server - SSH:
[email protected]:Wh1isper/mcp-email-server.git
Primary repository areas:
mcp_email_server/app.py— FastMCP server, resources, tools, and tool visibility.mcp_email_server/cli.py— stdio, SSE, Streamable HTTP, UI, reset, and credential migration commands.mcp_email_server/config.py— TOML settings, environment composition, account models, and persistence.mcp_email_server/keyring_store.py— operating system keyring integration.mcp_email_server/emails/— IMAP and SMTP behavior and response models.mcp_email_server/ui.py/ the replacement Web UI package — the local loopback management adapter and packaged static assets.frontend/— React/TypeScript management UI source and locked maintainer build.plugins/,.agents/, and.claude-plugin/— optional Codex/Claude Code plugin packaging, shared local MCP launch metadata, and safe non-secret setup guidance.tests/— unit, contract, integration, security, and browser-facing tests.docs/— user documentation published with MkDocs.spec/— unpublished normative architecture and product contracts kept as flat numbered documents.
Project Conventions
- Support Python 3.11 and later.
- Use
uvfor dependency management and command execution. - Follow the existing typed, asynchronous Python style.
- Prefer explicit types and
isinstancechecks over dynamic attribute checks. - Use Pydantic models for configuration and structured responses.
- Keep MCP-facing descriptions accurate because clients derive tool schemas from them.
- Preserve the distinction between persistent TOML settings and the environment-composited runtime view.
- Treat credential storage, allowlists, attachment paths, and HTTP transport settings as security-sensitive behavior.
- Do not log, document, or commit real email credentials, API keys, message contents, or tokens.
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.
- 6d ago First seen · 189 lines · 2,504 tokens per session scan A ec5f4642b281
mcp-email-server AGENTS.md is an instructions file published in the GitHub repository Wh1isper/mcp-email-server (321 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 2,504 tokens to every session, about $0.0125 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 2026-08-30.
Other instructions, from other repositories
proton-safe-mcp mermaid.instructions.md
Instructions for fbossiere/proton-safe-mcp, covering mermaid ai skills, workflow, lm tools — call these for every diagram interaction, vs code commands and diagram editing & preview.
email-mcp CLAUDE.md
Claude Code instructions for codefuturist/email-mcp, covering claude.md, what this repo is, stack and tooling, conventions to follow and what to do / not do.
proton-safe-mcp copilot-instructions.md
Copilot instructions for fbossiere/proton-safe-mcp: When the user asks to create, edit, or visualize a diagram, follow the instructions in .github/instructions/mermaid.instructions.md.
xtnd-mcp-one CLAUDE.md
Claude Code instructions for XTND-DYNAMICS/xtnd-mcp-one, covering claude.md — xtnd-mcp-one, golden rules and commands.
RivalSearchMCP AGENTS.md
AGENTS.md instructions for damionrashford/RivalSearchMCP, covering agents.md, project overview, development commands, setup & running and install dependencies.
mcp-outline CLAUDE.md
Instructions for Vortiago/mcp-outline, covering mcp outline server guide, purpose, architecture, tool categories and feature registration flow.