agentmods.dev

imap-mcp-server: Instructions file for Codex

AGENTS.md

imap-mcp-server AGENTS.md is an instructions file for Codex, OpenCode from nikolausm/imap-mcp-server. It costs 1,446 tokens per session, scanned A, original, MIT.

Repository instructions for an MCP mail server that lets AI assistants access email through IMAP and send messages through SMTP. They describe its architecture, build and test rules, and credential handling.

In plain words
What is it for?
They help work on mailbox access, message sending, account management, encrypted credential files, environment-variable overrides, service code, MCP tool registration, and repository checks.
Why use it?
They help agents change the mail server without breaking its account storage, connection services, tool registration, or security requirements. They also explain where credentials are stored and how temporary environment overrides work.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is nikolausm/imap-mcp-server's own configuration. It tells Codex and OpenCode how to work on imap-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything imap-mcp-server configures →

not rated 91 3d ago A scan 1,446 tokens original MIT
View the source file nikolausm/imap-mcp-server
Reuse

Borrowing it

Nothing to install: this file belongs to nikolausm/imap-mcp-server. 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/nikolausm/imap-mcp-server/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/nikolausm/imap-mcp-server

Made for: Codex, OpenCode.

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 imap-mcp-server AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nikolausm/imap-mcp-server/agents-md.svg)](https://agentmods.dev/instructions/nikolausm/imap-mcp-server/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/nikolausm/imap-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/nikolausm/imap-mcp-server/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,446 This file is loaded in full into every session.
When invoked 1,446 The same file — it is already loaded in full.
Security scan A 0 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 5.1 $0.01446 $0.01446
Opus 5 $0.00723 $0.00723
Sonnet 5 $0.00289 $0.00289
Haiku 4.5 $0.00145 $0.00145

Measured 6d ago against content hash 95d376a68dc7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

imap-mcp-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.

AGENTS.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Cross-agent project guide for imap-mcp-server — a Model Context Protocol (MCP) server that gives AI assistants (Claude, ChatGPT, Cursor, …) access to IMAP/SMTP mailboxes. This file is the shared source of truth for any agent or contributor working in this repository.

Architecture

  • Entry point — src/index.ts boots an McpServer (MCP SDK) over stdio and registers all tools via src/tools/index.ts.
  • Services (src/services/):
    • ImapService — IMAP protocol via imapflow, with connection pooling, folder operations, search, fetch, move/delete, append (Sent/Drafts).
    • SmtpService — outbound mail via nodemailer; composes raw MIME and sends.
    • AccountManager — account CRUD with AES-256-CBC encrypted credential storage at ~/.imap-mcp/accounts.json (key at ~/.imap-mcp/.key). Credentials can be overridden at read time via environment variables keyed by the account's normalized name (uppercase, non-alphanumeric → _): IMAP_MCP_ACCOUNT_<NAME>_IMAP_USERNAME / _IMAP_PASSWORD and IMAP_MCP_ACCOUNT_<NAME>_SMTP_USERNAME / _SMTP_PASSWORD. Overrides are in-memory only (never persisted) and apply only to existing accounts. The variables are consumed at startup (constructor): captured into an AES-256-encrypted in-memory cache and deleted from process.env so the plaintext secret does not linger in the environment. An empty credential is the marker for "env-managed"; assertCredentialsResolved (src/utils/env-credentials.ts) is called from ImapService.connect and SmtpService.createTransporter and fails with the missing variable's name instead of dialing out blank. Keep envVarName() in sync with its copy in public/js/app.js (the wizard is a static asset and cannot import it) — tests/env-credentials.test.ts asserts the two agree.
    • SpamService — disposable/known-spam domain detection.
  • Tools (src/tools/), grouped by area:
    • account-tools.ts — add / update / list / remove / connect / disconnect / test.
    • email-tools.ts — search, get, latest, send, reply, forward, save draft, mark read/unread, delete, bulk delete, move, attachments, upload, threads.
    • folder-tools.ts — list, status, create, unread counts.
    • spam-tools.ts — spam analysis, domain stats, allow/deny lists.
  • Web setup wizard — src/web/server.ts (Express) serves public/ for account onboarding (npm run setup / imap-setup).
  • Types — src/types/index.ts.
  • All tools return JSON-formatted text content; errors are returned as structured JSON where practical rather than thrown for caller-facing failures.

Read the full file on GitHub · 103 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. 6d ago First seen · 103 lines · 1,446 tokens per session scan A 95d376a68dc7

Subscribe to this mod's changes

imap-mcp-server AGENTS.md is an instructions file published in the GitHub repository nikolausm/imap-mcp-server (91 stars, last pushed 3d ago), licensed MIT. It adds 1,446 tokens to every session, about $0.0072 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.

LLMaiclaudeemailimapmcp
Related

Other instructions, from other repositories

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

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 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

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

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

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