amp-mcp-server: Instructions file for Codex

AGENTS.md

amp-mcp-server AGENTS.md is an instructions file for Codex, OpenCode from eddinsw/amp-mcp-server. It costs 4,023 tokens per session, scanned A, original, MIT.

Repository guidance for amp-mcp-server, a program that connects AI coding agents to an AMP service through the Model Context Protocol (MCP), a standard way for AI tools to use external services.

In plain words
What is it for?
Use it when changing or reviewing amp-mcp-server, especially its HTTP authentication, security checks, health endpoint, tests, Docker builds, or CI process.
Why use it?
It gives coding agents the project’s current architecture, security setup, tests, build commands, and deployment details in one place.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code; mentions AGENTS.md; mentions Codex.

This is eddinsw/amp-mcp-server's own configuration. It tells Codex and OpenCode how to work on amp-mcp-server 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 amp-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to eddinsw/amp-mcp-server. 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/eddinsw/amp-mcp-server/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/eddinsw/amp-mcp-server

Made for: Codex, OpenCode.

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 amp-mcp-server AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/eddinsw/amp-mcp-server/agents-md/github.svg)](https://agentmods.dev/instructions/eddinsw/amp-mcp-server/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/eddinsw/amp-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/eddinsw/amp-mcp-server/agents-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 amp-mcp-server AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/eddinsw/amp-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/eddinsw/amp-mcp-server/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,023 This file is loaded in full into every session.
When invoked 4,023 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.04023 $0.04023
Opus 5.5 $0.01609 $0.01609
Sonnet 5.5 $0.00805 $0.00805
Haiku 4.5 $0.00402 $0.00402

Measured 2mo ago against content hash e65edda105bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

amp-mcp-server AGENTS.md scanned grade A with 1 finding 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 2mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

├── Dockerfile # multi-stage; HEALTHCHECK uses node fetch (no curl in slim image)
AGENTS.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — amp-mcp-server

Context for AI coding agents (Claude Code, Codex, etc.) working on this repository.


Current state (v0.2.1, 2026-05-01)

  • What's running: stable. v0.2.1 ships HTTP auth (bearer + OAuth 2.1), security hardening (host/origin allow-lists, rate limiting, unsafe-binding guard), and a /health liveness endpoint. v0.1 was already verified end-to-end against Will's live homelab AMP at https://amp.darkforge.app.
  • Hosting: GitLab is primary (https://gitlab.darkforge.app/weddins/amp-mcp-server). A push mirror to GitHub (https://github.com/eddinsw/amp-mcp-server) is being set up so the public can see the code; PRs from outside contributors land on GitHub but merges happen on the GitLab side.
  • CI/CD: GitLab CI builds + pushes Docker images to the GitLab registry on every push to main and on tags. No GitHub Actions.
  • Tests: vitest with 23 passing unit tests covering auth middleware (bearer, OAuth, scope check, audience check, error paths). Integration smoke-tested manually for the security guards (rate limit, origin, host, unsafe-bind refuse).
  • Build: npm run build clean. npm test clean.

The earlier Phase A–D framing is retired — that was v0.1 packaging. We're past it.

What this is

An MCP (Model Context Protocol) server that wraps CubeCoders AMP (Application Management Panel) so MCP clients — Claude Desktop, Claude Code, Claude.ai, others — can list, inspect, and control AMP-managed game-server instances.

CubeCoders AMP is a paid, self-hosted game-server control panel. This project is a client of AMP's public REST API; no AMP source or binaries are redistributed. Users bring their own licensed AMP install.

Why it exists

No MCP server existed for AMP. Will runs AMP in his homelab. Building this gives Claude direct, structured access to start/stop game servers, send console commands, take backups, and read server state without screen-scraping the AMP web UI.

Architecture

MCP client (Claude.ai / Desktop / Code / custom)
        │  stdio  ── or ──  HTTP (stateless Streamable + bearer/OAuth)
        ▼
   amp-mcp-server
        │
        ├─ src/transports/{stdio,http}.ts   (transport entrypoints)
        ├─ src/server.ts                    (per-request McpServer factory)
        ├─ src/tools/{instances,console,operations}.ts (registered tools)
        ├─ src/auth/{bearer,oauth,shared}.ts (HTTP auth middleware)
        ├─ src/config.ts                    (zod-validated env loader)
        └─ src/amp-client.ts ── REST/JSON ──▶  AMP install (homelab)
                  └─▶ @neuralnexus/ampapi  (typed AMP client; native fetch, no transitive deps)

Read the full file on GitHub · 233 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. 2mo ago First seen · 233 lines · 4,023 tokens per session scan A e65edda105bc

Subscribe to this mod's changes

amp-mcp-server AGENTS.md is an instructions file published in the GitHub repository eddinsw/amp-mcp-server (5 stars, last pushed 6mo ago), licensed MIT. It adds 4,023 tokens to every session, about $0.0161 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

amp-mcp-server AGENTS.md compared with instructions from other repositories

amp-mcp-server AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
amp-mcp-server AGENTS.mdeddinsw/amp-mcp-serverInstructions file56mo agoMITA4,023Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,649GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA1,907GitHub Copilot