What is mcp-mailtrap CLAUDE.md?

Developer instructions for an MCP server that connects coding agents to Mailtrap, an email testing and delivery platform. They describe its structure, commands, and patterns for adding tools.

Use them when working on the mcp-mailtrap codebase, especially when adding Mailtrap tools, validating inputs, handling API requests, or formatting analytics results.

They give contributors a shared reference for building, testing, linting, and extending the server without having to rediscover its conventions.

How pijusz/mcp-mailtrap configures Claude Code

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/CLAUDE.md

Clone the repo

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

Made for: Claude Code.

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/claude-md/github.svg)](https://agentmods.dev/instructions/pijusz/mcp-mailtrap/claude-md)

Your own site

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

Per session 448 This file is loaded in full into every session.

When invoked 448 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	$0.00448	$0.00448
Opus 5.5	$0.00179	$0.00179
Sonnet 5.5	$0.00090	$0.00090
Haiku 4.5	$0.00045	$0.00045

Measured 14d ago against content hash f4d8fc4e09b6, 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 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 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.

CLAUDE.md · 39 lines

What it actually says

mcp-mailtrap

MCP server for the Mailtrap email platform. Analytics-first with full CRUD.

Quick Reference

Runtime: Bun (dev) / Node (built)
Entry: src/index.ts
Build: bun run build → binary; bun run build:npm → dist/index.js
Test: bun test
Lint: bun run check (biome) · Types: bun run typecheck

Architecture

Single unified API client routes to 4 Mailtrap base URLs automatically
All tools return { content: [{ type: "text", text }] } MCP format
fetchWithRetry handles 429/5xx with exponential backoff
Account ID resolved lazily on first tool call (env var → auto-discover)
4 base URLs: mailtrap.io (general), send.api (transactional), bulk.api (bulk), sandbox.api (sandbox)

Key Patterns

Tool files export registerXTools(server: McpServer) functions
Zod for parameter validation
formatTable for analytics output (Metric | Count | Rate %)
react-email renders component files (.tsx/.jsx/.js/.mjs) to HTML (not arbitrary strings)
SMTP credentials redacted in sandbox inbox responses
Multi-action tools use action param to consolidate CRUD operations

Adding New Tools

Add tool in appropriate file under src/tools/
Use readTool(server, name, description, zodShape, handler) or writeTool(...) from src/utils/register-tool.ts (wraps server.registerTool with MCP annotations)
Use request<T>() from mailtrap-api service
Use resolveAccountId() for account-scoped endpoints
Format output with formatTable() or JSON.stringify(data, null, 2)
Return { content: [{ type: "text" as const, text }] }; for bad input use errorResult() / requireArgs() from src/utils/tool-result.ts
Register in src/tools/index.ts

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 · +60 tokens per session f4d8fc4e09b6
2mo ago First seen · 39 lines · 388 tokens per session scan A d9a58bf9688a

Subscribe to this mod's changes

mcp-mailtrap CLAUDE.md is an instructions file published in the GitHub repository pijusz/mcp-mailtrap (3 stars, last pushed 15d ago), licensed MIT. It adds 448 tokens to every session, about $0.0018 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.

mcp-mailtrap CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-mailtrap CLAUDE.mdpijusz/mcp-mailtrap	Instructions file	3	15d ago	MIT	A	448	Claude Code
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 Claude Code