fastmail-mcp: Instructions file for Codex

AGENTS.md

fastmail-mcp AGENTS.md is an instructions file for Codex, OpenCode from as-j/fastmail-mcp. It costs 826 tokens per session, scanned A, original, MIT.

Repository instructions for working on Fastmail-MCP, a server that exposes 28 tools for Fastmail email through JMAP, Fastmail’s email interface. They describe the project’s commands, structure, and coding patterns.

In plain words
What is it for?
Building and testing the project, locating authentication and email code, and working on mailboxes, messages, attachments, searches, and MCP tool handlers.
Why use it?
They give a coding assistant the project context needed to build, test, and change the server consistently.

Instructions file for CodexOpenCode

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

This is as-j/fastmail-mcp's own configuration. It tells Codex and OpenCode how to work on fastmail-mcp 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 fastmail-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to as-j/fastmail-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.

Copy the file
curl -O https://raw.githubusercontent.com/as-j/fastmail-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/as-j/fastmail-mcp

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 fastmail-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/as-j/fastmail-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/as-j/fastmail-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/as-j/fastmail-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/as-j/fastmail-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for fastmail-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/as-j/fastmail-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/as-j/fastmail-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 826 This file is loaded in full into every session.
When invoked 826 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00826 $0.00826
Opus 5.5 $0.00330 $0.00330
Sonnet 5.5 $0.00165 $0.00165
Haiku 4.5 $0.00083 $0.00083

Measured 2mo ago against content hash 8e04599b3732, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fastmail-mcp 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 2mo 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 · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to Codex (Codex.ai/code) when working with code in this repository.

Commands

npm run build          # Compile TypeScript to dist/
npm run dev            # Run directly with tsx (no build needed)
npm start              # Run compiled output (requires build first)
npm test               # Run all tests
tsx --test src/jmap-client.test.ts  # Run a single test file

Architecture

This is a Model Context Protocol (MCP) server that exposes 28 tools for interacting with Fastmail email via the JMAP protocol.

Source Files

  • src/auth.ts — FastmailAuth class: holds API token, builds auth headers and endpoint URLs. Simple, rarely changes.
  • src/jmap-client.ts — Core JMAP client (JmapClient class). All email/mailbox/attachment/search operations live here. Makes JMAP method calls via makeRequest(), handles session bootstrapping, identity resolution, and JMAP result references (#ids with resultOf for chained calls).
  • src/mcp-server.ts — MCP server factory and tool handlers. Registers all 28 tools, handles request dispatch, coerces JSON-encoded string args from web clients, normalizes address arrays, and resolves Fastmail config into per-session runtime contexts.
  • src/http-server.ts — HTTP transport/session manager. Creates isolated MCP server instances per HTTP session, enforces body/session limits, expires idle sessions, and returns structured JSON-RPC errors for malformed HTTP requests.
  • src/index.ts — Startup entry point. Chooses stdio vs HTTP mode and delegates to the appropriate server bootstrap code.

Key Patterns

JMAP chaining: Many operations use JMAP result references — e.g., a query call returns an ID, and a subsequent get call references it with "#ids": {"resultOf": "...", "name": "...", "path": "/ids"}. This avoids two round trips.

Arg coercion in mcp-server.ts: The coerceArgs function handles the case where web UIs send tool arguments as JSON strings instead of parsed objects. Any new tools that accept arrays or objects need to be supported there.

Read the full file on GitHub · 49 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. 2mo ago First seen · 49 lines · 826 tokens per session scan A 8e04599b3732

Subscribe to this mod's changes

fastmail-mcp AGENTS.md is an instructions file published in the GitHub repository as-j/fastmail-mcp (0 stars, last pushed 7mo ago), licensed MIT. It adds 826 tokens to every session, about $0.0033 per session on Opus 5.5. 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.

Related

fastmail-mcp AGENTS.md compared with instructions from other repositories

fastmail-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
fastmail-mcp AGENTS.mdas-j/fastmail-mcpInstructions file07mo agoMITA826Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot