agentmods.dev

mcp-gateway: Instructions file for Claude Code

CLAUDE.md

mcp-gateway CLAUDE.md is an instructions file for Claude Code from Kuadrant/mcp-gateway. It costs 1,277 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for an MCP Gateway, a service that routes requests between AI clients and Model Context Protocol servers. It describes its Envoy-based gateway, routing components, server discovery, authentication, and configuration flow.

In plain words
What is it for?
Use them when working on MCP server discovery, request routing, tool aggregation, authentication headers, TLS trust settings, configuration secrets, or gateway components.
Why use it?
They give an agent the architecture and security rules needed to change the gateway without confusing its separate routing, brokering, and control functions.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is Kuadrant/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 →

not rated 98repo today A scan 1,277 tokens original Apache-2.0
View source ↗ Kuadrant/mcp-gateway kuadrant.io
Reuse

Borrowing it

Nothing to install: this file belongs to Kuadrant/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/Kuadrant/mcp-gateway/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Kuadrant/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/kuadrant/mcp-gateway/claude-md.svg)](https://agentmods.dev/instructions/kuadrant/mcp-gateway/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kuadrant/mcp-gateway/claude-md"><img src="https://agentmods.dev/badge/instructions/kuadrant/mcp-gateway/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,277 This file is loaded in full into every session.
When invoked 1,277 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 $0.01277 $0.01277
Opus 5 $0.00639 $0.00639
Sonnet 5 $0.00255 $0.00255
Haiku 4.5 $0.00128 $0.00128

Measured 8d ago against content hash 8b6fab5aa469, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 8d 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 · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project Overview

MCP Gateway: an Envoy-based gateway for Model Context Protocol (MCP) servers.

Two binaries, four components:

cmd/mcp-broker-router/main.go — data-plane:

  • Router: Envoy ext_proc, routes MCP requests (gRPC :50051)
  • Broker: aggregates tools from upstream MCP servers (HTTP :8080/mcp)

cmd/main.go — control-plane:

  • Controller: discovers MCP servers via MCPServerRegistration and MCPVirtualServer CRDs
  • Operator: reconciles MCPGatewayExtension, deploys router + broker instances

Architecture

Client → Gateway (Envoy) → Router (ext_proc) → Broker → Upstream MCP Servers
                ↑                                 ↑
           Controller → Secret ──────────────────┘
  • Controller watches CRDs, discovers backends via HTTPRoutes, writes config Secret
  • Broker reads config Secret, connects to upstreams, federates tools with prefixes
  • Router parses MCP requests, adds auth headers, tells Envoy where to route
  • Tool calls use lazy init: router hairpins an initialize request back through Envoy before the tool/call
  • All MCP traffic flows through Envoy for consistent policies

Istio is ONLY a Gateway API provider — no sidecars, no ambient mode, no service mesh. Just istiod programming the Gateway's Envoy proxy.

TLS Trust Pool

Broker and 2025-11-25 hairpin TLS trust is additive:

  1. System roots — always loaded
  2. Gateway CA bundle — MCPGatewayExtension.caCertBundleRef references a shared Secret, written once to config as gatewayCACertPEM. Used for broker→upstream connections and for 2025-11-25 protocol hairpin requests to the gateway HTTPS listener. 2026-07-28 MCP calls do not hairpin. If the listener CA and upstream CAs differ, concatenate both PEMs in that Secret.
  3. Per-server CA — MCPServerRegistration.caCertSecretRef appends for servers with unique CAs (upstream only, not hairpin)

Each layer appends to the previous. Gateway bundle changes trigger broker to recreate TLS upstream managers and rebuild the hairpin client.

Read the full file on GitHub · 116 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. 8d ago First seen · 116 lines · 1,277 tokens per session scan A 8b6fab5aa469

Subscribe to this mod's changes

mcp-gateway CLAUDE.md is an instructions file published in the GitHub repository Kuadrant/mcp-gateway (98 stars, last pushed today), licensed Apache-2.0. It adds 1,277 tokens to every session, about $0.0064 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 2026-08-30.

Related

Other instructions, from other repositories

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 · 5,153 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

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

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

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