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/boutquin/mcp-server-email/claude-mdgit clone --depth 1 https://github.com/boutquin/mcp-server-emailWrote 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/boutquin/mcp-server-email/claude-md)<a href="https://agentmods.dev/instructions/boutquin/mcp-server-email/claude-md"><img src="https://agentmods.dev/badge/instructions/boutquin/mcp-server-email/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 | $0.01160 | $0.01160 |
| Opus 5 | $0.00580 | $0.00580 |
| Sonnet 5 | $0.00232 | $0.00232 |
| Haiku 4.5 | $0.00116 | $0.00116 |
Grade A, and why
mcp-server-email 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 3d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcp-server-email
Go MCP server for email (IMAP/SMTP). 22 tools, multi-account, connection pooling, retry, rate limiting.
Module: github.com/boutquin/mcp-server-email | Go 1.24 | MIT
Package Layout
cmd/mcp-server-email/main.go → Entry point, slog init, pool init, signal handling, stdio serve
internal/
├── auth/ → OAuth2 device-code flow, SASL XOAUTH2, token store, provider detection
├── config/ → ENV/file-based multi-account config loading + provider auto-detection
├── models/ → Email/Folder/AttachmentInfo structs, message ID codec, error sentinels
├── imap/ → Client (split: client.go, client_*.go) + Pool + Connector + auth + MIME
├── log/ → Structured logging (slog) initialization from environment
├── smtp/ → Client + Pool (lightweight, connect-per-send) + OAuth2 auth retry
├── retry/ → Token-bucket rate limiter + exponential backoff with jitter
├── tools/ → All 22 MCP tool handlers + registration
└── resources/ → email://status resource
Architecture
Data flow: MCP client → stdio → mcp-go router → tool handler → imap.Operations/smtp.Operations interface → pool → client → IMAP/SMTP server.
Key patterns:
- Interface-driven DI —
imap.Operations(20 methods) andsmtp.Operations(3 methods) decouple handlers from protocol clients. Compile-time checks enforce conformance. - Connection pooling with singleflight — IMAP Pool coalesces concurrent requests for the same account via inflight map. Prevents thundering herd.
- Force-close with reconnect —
connInvalidatomic flag + raw socket close unblocks hung IMAP operations. - Connector adapter —
imapclientAdaptercollapses go-imap's two-step cmd/wait API into single-call interface for mocking. - Composite message IDs —
{account}:{mailbox}:{uid}format. All CRUD tools extract routing info from ID alone. - Retry with exponential backoff + jitter — Shared
retry.WithRetrywithPermanentErrorshort-circuit. - Token-bucket rate limiting — Per-account, per-protocol (IMAP req/min, SMTP sends/hour).
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.
- 3d ago First seen · 87 lines · 1,160 tokens per session scan A c94707fd9f50
mcp-server-email CLAUDE.md is an instructions file published in the GitHub repository boutquin/mcp-server-email (2 stars, last pushed 5mo ago), licensed MIT. It adds 1,160 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
baryon-mcp AGENTS.md
AGENTS.md instructions for combor/baryon-mcp, covering agents.md and editing guidance.
baryon-mcp CLAUDE.md
Claude Code instructions for combor/baryon-mcp: All important information for working in this repository is in AGENTS.md.
graymatter AGENTS.md
AGENTS.md instructions for angelnicolasc/graymatter, covering agents.md, your tools, when to call which, first call and identity.
mcp-email-server AGENTS.md
AGENTS.md instructions for Wh1isper/mcp-email-server, covering repository overview, project conventions, current architecture direction, development workflow and documentation requirements.
graymatter CLAUDE.md
Claude Code instructions for angelnicolasc/graymatter, covering claude.md, a user asked you to set graymatter up, you are working in a project that already uses graymatter and you are contributing to graymatter itself.
imap-mcp-server AGENTS.md
Instructions for nikolausm/imap-mcp-server, covering agents.md, architecture, build / test commands, security rules (must follow) and conventions.