mcp-gateway: Instructions file for Claude Code

CLAUDE.md

mcp-gateway CLAUDE.md is an instructions file for Claude Code from datatorag/mcp-gateway. It costs 733 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 for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths.

This is datatorag/mcp-gateway's own configuration. It tells Claude Code how to work on mcp-gateway itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-gateway configures →

Reuse

Borrowing it

Nothing to install: this file belongs to datatorag/mcp-gateway. 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/datatorag/mcp-gateway/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/datatorag/mcp-gateway

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.

agentmods badge for mcp-gateway CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/datatorag/mcp-gateway/claude-md/github.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/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.

agentmods 80×15 button for mcp-gateway CLAUDE.md

Your own site · 80×15
<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="Reviewed on agentmods" width="80" height="20"></a>
Per session 733 This file is loaded in full into every session.
When invoked 733 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00733 $0.00733
Opus 5.5 $0.00293 $0.00293
Sonnet 5.5 $0.00147 $0.00147
Haiku 4.5 $0.00073 $0.00073

Measured 27d ago against content hash 11423338a8c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 27d 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 connector plugins under plugins/ (gws-mcp, atlassian-mcp) + their 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. 27d ago Changed · +12 tokens per session 11423338a8c4
  2. 2mo 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 (4 stars, last pushed yesterday), licensed MIT. It adds 733 tokens to every session, about $0.0029 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.

Related

mcp-gateway CLAUDE.md compared with instructions from other repositories

mcp-gateway CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-gateway CLAUDE.mddatatorag/mcp-gatewayInstructions file4yesterdayMITA733Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode