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.
npx agentmods add instructions/thargy/mcp-gateway/agents-mdgit clone --depth 1 https://github.com/thargy/mcp-gatewayWrote 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.
[](https://agentmods.dev/instructions/thargy/mcp-gateway/agents-md)<a href="https://agentmods.dev/instructions/thargy/mcp-gateway/agents-md"><img src="https://agentmods.dev/badge/instructions/thargy/mcp-gateway/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00574 | $0.00574 |
| Opus 5 | $0.00287 | $0.00287 |
| Sonnet 5 | $0.00115 | $0.00115 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
mcp-gateway AGENTS.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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md: Operational Guidelines for AI Assistants
This repository (mcp-gateway) implements a Universal Multi-Tenant Model Context Protocol (MCP) reverse proxy and gateway service built on @thargy/mcp-server-core to adapt arbitrary 3rd-party MCP servers (HTTP and STDIO) for seamless operation behind Cloudflare Zero Trust tunnels and modern AI IDEs.
Critical Safety Invariants
- NEVER COMMIT OR PUSH TO GIT: Do not run
git commit,git push, or alter git history without express instruction from the user. - Strict ESM & TypeScript: The project uses NodeNext ESM (
import ... from './file.js'). Every local import statement MUST include an explicit.jsextension. - Seam-First Adapter Architecture: All upstream backends implement the
IMcpBackendAdapterinterface (HttpProxyAdapter,StdioProxyAdapter). - Test Speed & Network Isolation: Unit tests must execute in complete isolation from external networks using in-memory doubles or mocked HTTP/STDIO streams.
Architectural Rules
1. Unified Gateway Philosophy
- A single gateway service runs on the Docker server (
ssh-docker.thargy.com:3007), exposing multi-tenant MCP endpoints and dedicated port listeners. - Cloudflare Tunnel streams traffic via
https://mcp.thargy.com/<path>/mcp. - All requests benefit from
@thargy/mcp-server-corefeatures:- Immediate
: heartbeat\n\nCloudflare SSE stream priming. subscriptions/listennotification streams.- Stateless JSON-RPC and stateful Streamable HTTP dual-mode content negotiation.
- Constant-time Bearer token authentication.
- Immediate
2. Declarative Route Configuration (config.yaml)
Adding new 3rd-party MCP servers (e.g. Brave Search, SQLite, PostgreSQL) requires only adding a route definition to config.yaml:
routes:
gh:
type: http
name: "github-mcp-server"
targetUrl: "http://github-mcp-backend:8082"
authHeaderEnv: "GITHUB_PERSONAL_ACCESS_TOKEN"
brave:
type: stdio
name: "brave-search"
command: "npx"
args: ["-y", "@modelcontextprotocol/server-brave-search"]
env:
BRAVE_API_KEY: "${BRAVE_API_KEY}"
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.
- 3d ago First seen · 63 lines · 574 tokens per session scan A 3453263039e6
mcp-gateway AGENTS.md is an instructions file published in the GitHub repository thargy/mcp-gateway (0 stars, last pushed 11d ago), licensed MIT. It adds 574 tokens to every session, about $0.0029 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.
Other instructions, from other repositories
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.