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/sandraschi/godot-mcp/agents-mdgit clone --depth 1 https://github.com/sandraschi/godot-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/sandraschi/godot-mcp/agents-md)<a href="https://agentmods.dev/instructions/sandraschi/godot-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sandraschi/godot-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 | $0.00838 | $0.00838 |
| Opus 5 | $0.00419 | $0.00419 |
| Sonnet 5 | $0.00168 | $0.00168 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
godot-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 6d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — godot-mcp Context
Repo: godot-mcp — AI-driven Godot 4.4 engine control via MCP + game builder pipeline
Version: 0.5.0-beta.1 (95+ MCP tools)
Python: 3.10+ | FastMCP: 3.2.0+ | Godot: 4.4 | Frontend: Vite 7 + React 19
Essential Paths
| Path | Purpose |
|---|---|
src/godot_mcp/server.py |
FastMCP server + FastAPI gateway (port 10993) |
src/godot_mcp/services/godot_bridge.py |
TCP bridge client to Godot (port 9080) |
src/godot_mcp/bridge/mcp_bridge.gd |
GDScript autoload — TCP server inside Godot |
src/godot_mcp/game_builder/ |
AI game-from-prompt pipeline (6 tools) |
src/godot_mcp/fleet/ |
Cross-server fleet pipeline (6 tools) |
src/godot_mcp/itch/ |
Butler/itch.io shipping (6 tools) |
src/godot_mcp/tools/core_tools.py |
Engine control + deterministic playtesting tools (31) |
src/godot_mcp/tools/docs_tools.py |
Godot documentation fetcher tool |
src/godot_mcp/services/splat_import.py |
3D Gaussian splat parser (.ply/.spz) |
src/godot_mcp/bridge/shaders/gaussian_splat.gdshader |
Gaussian splat rendering shader |
src/godot_mcp/sampling/ |
LLM sampling tools (2) |
src/godot_mcp/mcp_bridge/ |
Cross-server MCP bridge tools (2) |
src/godot_mcp/workflows/ |
Workflow engine + 3 built-in workflows |
webapp/ |
Vite React dashboard (port 10992) |
templates/ |
Godot project templates + export presets |
samples/ |
Sample games + MCPB bundles |
native/ |
Tauri 2.0 desktop wrapper |
docs/SPEC_GAME_BUILDER.md |
Game Builder architecture spec |
docs/SPEC_DETERMINISTIC_PLAYTESTING.md |
Deterministic playtesting implementation plan |
justfile |
Task runner — just serve, just godot-bridge, etc. |
Module Registration
All tools register via src/godot_mcp/tools/__init__.py → register_all(mcp). Each module has a register(mcp) function. New modules MUST be added to the register_all imports and calls.
Key Dependencies
- worldlabs-mcp (port 10865): Called via
MCPBridgeClientfromgodot_mcp.mcp_bridgefor Marble world generation - Godot 4.4 (port 9080): TCP bridge using
mcp_bridge.gdautoload - Butler (
BUTLER_API_KEY): itch.io CLI for shipping
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.
- 6d ago First seen · 51 lines · 838 tokens per session scan A 59c902b42c4f
godot-mcp AGENTS.md is an instructions file published in the GitHub repository sandraschi/godot-mcp (6 stars, last pushed 2d ago), licensed MIT. It adds 838 tokens to every session, about $0.0042 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
cocos-extensions AGENTS.md
Instructions for hhhh124hhhh/cocos-extensions, covering cocos mcp stack — agent 安装指南, 1. 这套东西由什么组成, 2. 前置条件, 3. 一键安装（推荐 agent 直接跑） and 4. 手动安装（无脚本时）.
excel-mcp-server CLAUDE.md
Instructions for TangentDomain/excel-mcp-server, covering excel mcp server, 技术栈, 目录结构, mcp 工具 → python api 映射 and sql 核心原则.
excel-mcp-server AGENTS.md
Instructions for TangentDomain/excel-mcp-server, covering excelmcp, turn 起始流程, 项目事实（l0）, 技术栈 and 目录结构.
steam-mcp AGENTS.md
AGENTS.md instructions for sandraschi/steam-mcp, covering steam-mcp agent context, repo, ports, auth and ai / chat (webapp).
steam-mcp CLAUDE.md
Claude Code instructions for sandraschi/steam-mcp, covering steam-mcp — claude code guide, entry points, standards and key files.
GameDesignOS AGENTS.md
Instructions for DY-2026/GameDesignOS, covering gamedesignos agent 入口, 默认接法, agent 执行规则, 什么时候用整个项目 and 每个 skill 单独怎么用.