What is tram-mcp CLAUDE.md?

Project instructions for tram-mcp, a TypeScript MCP server that connects coding agents to TestRail, a test-management service. They describe its layout, commands, credentials, and generated API catalog.

They are for developing, configuring, testing, and regenerating the TestRail endpoint catalog for tram-mcp. The server runs locally over standard input/output.

They give an agent the project-specific rules for running the server and handling TestRail authentication and API requests.

How trtmn/tram-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to trtmn/tram-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/trtmn/tram-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/trtmn/tram-mcp

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

Your own site

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

Per session 1,776 This file is loaded in full into every session.

When invoked 1,776 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	$0.01776	$0.01776
Opus 5.5	$0.00710	$0.00710
Sonnet 5.5	$0.00355	$0.00355
Haiku 4.5	$0.00178	$0.00178

Measured 2mo ago against content hash e466555ea3d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tram-mcp 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 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.

CLAUDE.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

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

Project Overview

This is an MCP (Model Context Protocol) server for TestRail, written in TypeScript. It runs locally over stdio — the default for coworkers. Run via npx tram-mcp (or the Claude Desktop .mcpb). Credentials come from a one-time browser login (tram-mcp login, saved to ~/.tram-mcp/credentials.json) or TESTRAIL_* env vars.

Key design principle: the server doesn't import a TestRail SDK at runtime. Instead scripts/generate_catalog.py AST-parses the testrail_api_module source (sibling checkout at ~/git/testrail_api_module) into src/catalog.json, and dispatch is generic (path params fill the endpoint template; the rest go to query string for GET / JSON body for POST). Regenerate with npm run catalog when the Python module changes. This is the one build-time Python dependency; there is no Python at runtime.

History: this was formerly a Python/PyPI package (FastMCP + testrail_api_module), then briefly also a Cloudflare Worker. Both are removed; tram-mcp is now solely an npm package running local stdio.

Repository layout

The TypeScript project lives at the repo root. Key files in src/:

tools.ts — MCP tool registration (transport-agnostic)
testrail.ts — TestRail HTTP client (fetch + Basic auth)
env.ts — credential resolution (getCredentials: client-supplied props, else TESTRAIL_*)
catalog.ts / catalog.json — generated endpoint catalog + generic dispatch
stdio.ts — stdio adapter; resolveLocalEnv() does env → credstore → none
credstore.ts — ~/.tram-mcp/credentials.json (0600) read/write
wizard.ts — the tram-mcp login browser credential form (loopback, CSRF + Host-checked)
cli.ts — the tram-mcp bin: default = stdio server; login / logout / status

Tech Stack

TypeScript, Node ≥ 18 (core relies on Node globals: fetch, btoa, crypto)
@modelcontextprotocol/sdk (stdio transport), zod
Build: esbuild (bundles dist/cli.js, inlining the catalog); tests: vitest

Read the full file on GitHub · 135 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.

2mo ago First seen · 135 lines · 1,776 tokens per session scan A e466555ea3d3

Subscribe to this mod's changes

tram-mcp CLAUDE.md is an instructions file published in the GitHub repository trtmn/tram-mcp (1 stars, last pushed 7d ago), licensed MIT. It adds 1,776 tokens to every session, about $0.0071 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.

tram-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
tram-mcp CLAUDE.mdtrtmn/tram-mcp	Instructions file	1	7d ago	MIT	A	1,776	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

tram-mcp: Instructions file for Claude Code