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/mlger/nakama-mcp/agents-mdgit clone --depth 1 https://github.com/mlger/nakama-mcpWrote 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/mlger/nakama-mcp/agents-md)<a href="https://agentmods.dev/instructions/mlger/nakama-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/mlger/nakama-mcp/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 5.1 | $0.01580 | $0.01580 |
| Opus 5 | $0.00790 | $0.00790 |
| Sonnet 5 | $0.00316 | $0.00316 |
| Haiku 4.5 | $0.00158 | $0.00158 |
Grade A, and why
nakama-mcp 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 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Workspace guide for ZCode agents working in nakama-mcp. For deeper detail, read CLAUDE.md — it is the authoritative architecture reference.
What this is
An MCP (Model Context Protocol) server that exposes a running Heroic Labs Nakama instance to MCP hosts. TypeScript, ESM, strict mode. No runtime framework beyond @modelcontextprotocol/sdk + zod; HTTP transport uses bare node:http. Wraps Nakama's two HTTP APIs:
- Client API (
:7350) — player-facing (auth, accounts, storage, leaderboards, RPCs). - Console API (
:7351) — admin/ops (search players, storage, status, ban).
Speaks stdio by default, or streamable-HTTP when MCP_TRANSPORT=http. Nakama exposes ~180 operations, so the server uses a search + execute design (nakama_search_actions → nakama_execute_action) over a generated catalog, plus ~12 promoted convenience tools.
Key directories
src/— TypeScript source (see layer map below).data/catalog.json— generated & committed, shipped in the npm package. Do not hand-edit; runnpm run regen-catalog.scripts/— catalog regen (regen-catalog.mjs,lib/resolve.mjs) and MCPB bundling (build-mcpb.mjs).test/— each test is a standalone Node script (no test framework); see commands below.docs/superpowers/— design/plan notes for past features.
Commands
npm install
npm run build # tsc -> dist/ (strict). ALWAYS build before testing — tests load dist/.
npm run dev # tsc --watch
npm test # fast suite, no server (resolve + redact + smoke + http + http-reaper + version)
npm run test:integration # needs `docker compose up -d --wait` first (stdio, Nakama 3.37.0 + CockroachDB)
npm run test:http-integration # same prerequisite; drives the live server over the HTTP transport
npm run regen-catalog # rebuild data/catalog.json from Nakama upstream (needs network)
npm run regen-catalog -- v3.37.0 # ...from a specific git ref/tag
npm run mcpb # build + pack desktop bundle -> dist-mcpb/nakama-mcp.mcpb
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.
- 5d ago First seen · 82 lines · 1,580 tokens per session scan A c89c1b121d7f
nakama-mcp AGENTS.md is an instructions file published in the GitHub repository mlger/nakama-mcp (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,580 tokens to every session, about $0.0079 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
Unity-AI-Animation CLAUDE.md
Instructions for IvanMurzak/Unity-AI-Animation, covering claude.md, what this is, build / run, critical invariants and find detail in.
better-godot-mcp AGENTS.md
AGENTS.md instructions for n24q02m/better-godot-mcp, covering agents.md - better-godot-mcp, build / lint / test commands, run a single test file, run a single test by name and mise shortcuts.
ai-rotom CLAUDE.md
Claude Code instructions for nonz250/ai-rotom, covering ai-rotom, 基本思想, 技術スタック, 開発コマンド and リポジトリ構成.
minecraft-dev-mcp CLAUDE.md
Instructions for MCDxAI/minecraft-dev-mcp, covering claude code context - minecraft dev mcp, project overview, release status, architecture and core services (src/services/).
Unity-AI-ProBuilder CLAUDE.md
Instructions for IvanMurzak/Unity-AI-ProBuilder, covering claude.md, what this is, build / run, critical invariants and find detail in.
Unity-AI-Tools-Template CLAUDE.md
Instructions for IvanMurzak/Unity-AI-Tools-Template, covering unity-ai-tools-template, build / run, 1. initialize a new package from the template, 2. open both unity projects so .meta files are generated and 3. bump version across all files in lock-step.