etracker-mcp CLAUDE.md

etracker-mcp CLAUDE.md is an instructions file for coding agents from fmeies/etracker-mcp. It costs 1,065 tokens per session, scanned A, original, MIT.

A set of Claude Code instructions for developing and running an etracker MCP server, a service that exposes etracker reporting data to an AI assistant.

In plain words
What is it for?
Use it when working on this Node.js and TypeScript server, including local development, builds, container images, and Helm deployments.
Why use it?
It keeps project structure, installation, development, build, production, Docker, and Kubernetes deployment guidance in one place.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/fmeies/etracker-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/fmeies/etracker-mcp

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 etracker-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/fmeies/etracker-mcp/claude-md.svg)](https://agentmods.dev/instructions/fmeies/etracker-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/fmeies/etracker-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/fmeies/etracker-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,065 This file is loaded in full into every session.
When invoked 1,065 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 $0.01065 $0.01065
Opus 5 $0.00532 $0.00532
Sonnet 5 $0.00213 $0.00213
Haiku 4.5 $0.00106 $0.00106

Measured 4d ago against content hash e7df08cdb3af, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

etracker-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 4d 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 · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

etracker MCP Server

Project structure

etracker-mcp/          # repo root — Node.js/TypeScript MCP server
  src/
    index.ts           # Express app, session store, /mcp + /health endpoints
    auth.ts            # authMiddleware — X-Api-Key + X-ET-Token headers
    ratelimit.ts       # Three-layer bucket rate limiter (burst / global / per-partner)
    cache.ts           # In-memory TTL cache (5 min), cache keys scoped per token
    analytics-api.ts   # etracker Reporting API client (BASE_URL: ws.etracker.com/api/v7)
    tools.ts           # MCP tool registrations, Zod schemas, column resolution
  helm/                # Helm chart for Kubernetes deployment
    values.yaml
  Dockerfile           # Multi-stage build, node:24-alpine

Commands

# Install
npm install

# Dev (tsx, hot-reload via node --import tsx/esm)
npm run dev

# Build
npm run build        # tsc → dist/

# Production
npm start            # node --env-file=.env dist/index.js

# Docker
docker build -t etracker-mcp .
docker run -p 3000:3000 -e PARTNER_API_KEYS='{"key":"partner-a"}' etracker-mcp

# Helm
helm install etracker-mcp ./helm -f my-values.yaml

Environment variables

Variable Required Description
PARTNER_API_KEYS yes JSON object: {"<key>":"<partner-id>"} — generate keys with openssl rand -hex 32
PORT no HTTP port (default: 3000)
ETRACKER_REPORT_PAGEVIEWS no Override default pageviews report ID (default: EATime)
ETRACKER_REPORT_CONVERSIONS no Override default conversions report ID (default: EAConversions)
ETRACKER_REPORT_AD no Override default ad report ID (default: EAMarketing)

Copy .env.example to .env for local development. The etracker token is not stored in env — partners pass it per request via X-ET-Token.

Authentication model

Every request to /mcp requires two headers:

  • X-Api-Key — MCP server access key (validated against PARTNER_API_KEYS, resolves to a partnerId used for rate limiting)
  • X-ET-Token — etracker account token (forwarded directly to the etracker API; never stored server-side)

Read the full file on GitHub · 98 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. 4d ago First seen · 98 lines · 1,065 tokens per session scan A e7df08cdb3af

Subscribe to this mod's changes

etracker-mcp CLAUDE.md is an instructions file published in the GitHub repository fmeies/etracker-mcp (0 stars, last pushed 4mo ago), licensed MIT. It adds 1,065 tokens to every session, about $0.0053 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 2026-08-31.