What is mcp-mailtrap AGENTS.md?

An instruction guide for using the mcp-mailtrap service to inspect email delivery and engagement. Mailtrap is an email testing and sending service that reports events such as delivery, bounces, opens, and clicks.

It helps review delivery statistics, investigate failed messages, compare results by domain or email provider, track opens and clicks over time, and check contact-list hygiene.

It provides a structured way to find why messages were not delivered and where delivery or engagement problems occur. It also helps identify suppressed contacts that still appear on mailing lists.

How pijusz/mcp-mailtrap configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to pijusz/mcp-mailtrap. 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/pijusz/mcp-mailtrap/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/pijusz/mcp-mailtrap

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/pijusz/mcp-mailtrap/agents-md/github.svg)](https://agentmods.dev/instructions/pijusz/mcp-mailtrap/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/pijusz/mcp-mailtrap/agents-md"><img src="https://agentmods.dev/badge/instructions/pijusz/mcp-mailtrap/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/pijusz/mcp-mailtrap/agents-md"><img src="https://agentmods.dev/badge/instructions/pijusz/mcp-mailtrap/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,373 This file is loaded in full into every session.

When invoked 1,373 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.

Model	Per session	Once invoked
Fable 5.1	$0.01373	$0.01373
Opus 5.5	$0.00549	$0.00549
Sonnet 5.5	$0.00275	$0.00275
Haiku 4.5	$0.00137	$0.00137

Measured 14d ago against content hash c5155e408861, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-mailtrap 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 14d 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 · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mcp-mailtrap — Agent Guide

Workflow-oriented guide for AI agents using this MCP server.

Authentication

Set MAILTRAP_API_TOKEN env var. Optionally set MAILTRAP_SENDING_TOKEN for transactional/bulk send.api requests and MAILTRAP_ACCOUNT_ID for a default account — otherwise the account is auto-discovered on first tool call.

Workflows

Investigating Deliverability

Start with get_stats for overall delivery/bounce/spam rates
Drill down with get_stats(group_by: "domain") or get_stats(group_by: "esp") to find problem areas
Use get_email_logs with status: "not_delivered" for specific failed emails
Check get_email_log for individual message event timelines

Monitoring Open & Click Rates

Use get_stats for aggregate open/click rates
Use get_stats(group_by: "date") for trends over time
Filter by categories to compare different email types
Use get_stats(group_by: "esp") to identify ESP-specific deliverability issues

Managing Contact Lists

Use list_contact_lists to see available lists
Use check_list_hygiene to find suppressed emails that still belong to contact lists
Follow suggested actions to clean up lists
Use import_contacts for bulk additions, export_contacts for bulk exports
Use manage_contact_field to manage custom fields for segmentation

Testing Emails

Use send_test_email to send to a sandbox inbox (optionally using MAILTRAP_TEST_INBOX_ID / MAILTRAP_DEFAULT_FROM_EMAIL defaults)
Use get_messages to see the email in the inbox
Use analyze_message for combined spam score + HTML compatibility + headers report
Use get_message(format: "htmlsource") to inspect raw HTML
Iterate on email content based on analysis results

Template Management

Use list_templates to see existing templates
Use create_template with body_html for raw HTML templates
For react-email templates: write a component file (.tsx, .jsx, .js, or .mjs), use render_react_email to produce HTML, then create_template
Use send_email with template_uuid to send using the template
Track template performance via get_stats(group_by: "category")

Read the full file on GitHub · 117 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.

14d ago Changed · +37 tokens per session c5155e408861
2mo ago First seen · 117 lines · 1,336 tokens per session scan A f5b9e6e5339e

Subscribe to this mod's changes

mcp-mailtrap AGENTS.md is an instructions file published in the GitHub repository pijusz/mcp-mailtrap (3 stars, last pushed 15d ago), licensed MIT. It adds 1,373 tokens to every session, about $0.0055 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.

Analytics and metrics

mcp-mailtrap AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-mailtrap AGENTS.mdpijusz/mcp-mailtrap	Instructions file	3	15d ago	MIT	A	1,373	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

mcp-mailtrap: Instructions file for Codex