mcp-gateway CLAUDE.md

mcp-gateway CLAUDE.md is an instructions file for coding agents from datatorag/mcp-gateway. It costs 721 tokens per session, scanned A, original, MIT.

A repository instruction file for datatorag-mcp, a project that includes an MCP gateway for connecting AI agents to tools and data.

In plain words
What is it for?
Use it when changing this repository, reviewing outgoing changes, handling secrets, running tests, or preparing a production deployment.
Why use it?
It records rules for working safely in a public repository, including security checks before pushing code or deploying it.

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/datatorag/mcp-gateway/claude-md
Clone the repo
git clone --depth 1 https://github.com/datatorag/mcp-gateway

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 mcp-gateway CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/datatorag/mcp-gateway/claude-md.svg)](https://agentmods.dev/instructions/datatorag/mcp-gateway/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/datatorag/mcp-gateway/claude-md"><img src="https://agentmods.dev/badge/instructions/datatorag/mcp-gateway/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 721 This file is loaded in full into every session.
When invoked 721 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 $0.00721 $0.00721
Opus 5 $0.00360 $0.00360
Sonnet 5 $0.00144 $0.00144
Haiku 4.5 $0.00072 $0.00072

Measured 5d ago against content hash 1f0453465647, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-gateway 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 5d 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 · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

datatorag-mcp

This repository is public. Everything committed here — code, docs, skills, agent definitions, commit messages — is visible to the world.

Security gate (mandatory)

Before every git push and before every production deploy:

  1. Run the security-reviewer agent (.claude/agents/security-reviewer.md) on the outgoing diff (origin/main...HEAD, or the staged/working-tree changes if pushing amends).
  2. Only push/deploy on VERDICT: PASS.
  3. On VERDICT: BLOCK, fix the findings first. If a secret is in any commit of the unpushed range, rewrite the range's history (amend or rebase) — deleting it in a follow-up commit is not enough. If a secret was already pushed, treat it as compromised: rotate it, then purge history.

Repo rules

  • Never commit secrets, rendered .env content, or credentials of any kind. Production secrets live in AWS SSM Parameter Store and are rendered at deploy time (see .env.example header and the deploy skill).
  • Never commit internal company documents, compliance evidence, or customer/lead personal data. Internal material belongs in the private company repo, not here.
  • Package manager is pnpm. Tests: pnpm vitest run in apps/gateway; typecheck: pnpm exec tsc --noEmit; production build: pnpm build.
  • Before pushing, verify the active GitHub account is the org account (gh auth status), not a personal one.

Skills & agents

Codebase knowledge lives in .claude/skills/ — load these instead of re-reading the source:

  • codebase-map — architecture, flows, decisions, where-things-live. Load first.
  • gateway-dev — recipes for gateway changes + test patterns + ship ritual.
  • site-content — blog/changelog/docs systems and page conventions.
  • services-integrations — Brevo/Slack/Stripe/PostHog/event-pipeline patterns.
  • ops-debugging — prod runbook (placeholder form; live values in memory).
  • gws-mcp-dev — developing the gws-mcp plugin repo + its ship tail.
  • product-capture — Remotion project at tools/capture for product screenshots/recordings; imports real gateway components so captures can't drift.
  • parent-updates — keeping the datatorag-hq parent session current. It cannot see this session, so an update not sent did not happen.
  • outbound-copy — anything a person outside the company reads: transactional/lifecycle email, in-product strings, form and error copy. Load it (and manuel-voice) before drafting a line.
  • Plus: blog-writing, db-query, deploy, humanizer, marketing-video (brand explainers only), product-promo-video (superseded).

Read the full file on GitHub · 56 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. 5d ago First seen · 56 lines · 721 tokens per session scan A 1f0453465647

Subscribe to this mod's changes

mcp-gateway CLAUDE.md is an instructions file published in the GitHub repository datatorag/mcp-gateway (3 stars, last pushed today), licensed MIT. It adds 721 tokens to every session, about $0.0036 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens