Godot-MCP: Instructions file for Claude Code

CLAUDE.md

Godot-MCP CLAUDE.md is an instructions file for Claude Code from IvanMurzak/Godot-MCP. It costs 4,753 tokens per session, scanned B, original, Apache-2.0.

A Godot editor add-on that connects an AI assistant to the Godot game engine through the Model Context Protocol, a standard way for software tools to exchange commands and data. The repository also contains a command-line package and automated tests.

In plain words
What is it for?
Developing, building and testing the Godot add-on and its command-line tool, including editor integration, server connection, reflection-based Godot tools and CI checks.
Why use it?
It lets an AI work with a Godot project through the editor while keeping work on the editor's main thread. The instructions explain the repository parts, external server connection and fixed dependency versions.

Instructions file for Claude Code

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

This is IvanMurzak/Godot-MCP's own configuration. It tells Claude Code how to work on Godot-MCP 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 Godot-MCP configures →

Reuse

Borrowing it

Nothing to install: this file belongs to IvanMurzak/Godot-MCP. 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/IvanMurzak/Godot-MCP/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/IvanMurzak/Godot-MCP

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 Godot-MCP CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ivanmurzak/godot-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/ivanmurzak/godot-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ivanmurzak/godot-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ivanmurzak/godot-mcp/claude-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 Godot-MCP CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ivanmurzak/godot-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ivanmurzak/godot-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,753 This file is loaded in full into every session.
When invoked 4,753 The same file — it is already loaded in full.
Security scan B 2 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 $0.04753 $0.04753
Opus 5 $0.02377 $0.02377
Sonnet 5 $0.00951 $0.00951
Haiku 4.5 $0.00475 $0.00475

Measured 9d ago against content hash a34ae6d8b223, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

Godot-MCP CLAUDE.md scanned grade B with 2 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 9d 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

curl -s -X POST http://localhost:5300/api/system-tools/ping -H "Content-Type: application/json" -d '{}'

Makes network callslowCapability

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

curl -s -X POST http://localhost:5300/api/system-tools/ping -H "Content-Type: application/json" -d '{}'
CLAUDE.md · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Godot-MCP

Godot-MCP bridges LLMs (Claude, Cursor, Copilot, …) with the Godot editor via the Model Context Protocol — the Godot-engine sibling of Unity-MCP. Sub-projects: addons/godot_mcp/ (the Godot editor addon, a Godot.NET.Sdk C# project), cli/ (the godot-cli npm package — the Godot analog of unity-mcp-cli), and Godot-MCP.Tests/ (the CI xUnit suite). The MCP server is NOT in this repo — the addon consumes the shared GameDev-MCP-Server. See CLI (godot-cli) and Server (shared GameDev-MCP-Server) below.

The addon is the heart of the repo. A [Tool] EditorPlugin (GodotMcpPlugin) boots on editor load, installs the main-thread dispatcher, builds a Reflector with Godot type converters, and connects to an MCP server (cloud ai-game.dev by default, or a custom local server) over the reused com.IvanMurzak.McpPlugin SignalR client. The MCP/reflection stack is not forked — it is consumed from nuget.org as PackageReferences and the pins are owned by the upstream release pipelines (never bump them here). The reused pins are frozen at com.IvanMurzak.ReflectorNet 5.4.0 and com.IvanMurzak.McpPlugin 8.3.0 (in Godot-MCP.csproj, mirrored by Godot-MCP.Tests/ and the infra testbed) — keep all three in lockstep; never bump here. (6.10.0 carries the shared engine-agnostic com.IvanMurzak.McpPlugin.AgentConfig module the addon consumes for AI-agent configurators — registry + AiAgentConfig + AgentConfiguratorDescription — replacing the addon's retired local copy; it also carries the WaitForImmediateTeardown API + opt-in bounded-reconnect this addon uses for the godot#78513 reload fix.)

Tool families

Tools live in addons/godot_mcp/Runtime/Tools/ (pure-managed families) and addons/godot_mcp/Editor/Tools/ (editor-only families) — one [AiToolType] partial class Tool_<Family> per family, with each tool method ([AiTool("<name>", ...)] + [Description]) in its own partial-class file. Tool names mirror Unity-MCP where sensible. 42 built-in tools across 12 families — the 12 families:

Read the full file on GitHub · 259 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. 9d ago First seen · 259 lines · 4,753 tokens per session scan B a34ae6d8b223

Subscribe to this mod's changes

Godot-MCP CLAUDE.md is an instructions file published in the GitHub repository IvanMurzak/Godot-MCP (236 stars, last pushed 5d ago), licensed Apache-2.0. It adds 4,753 tokens to every session, about $0.0238 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). 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

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

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

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

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

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