What is mcp-server-godot-editor CLAUDE.md?

Instructions for a Godot 4.5 editor plugin that lets AI agents control the Godot game editor. Godot is a tool for making games, and MCP is a standard way for software tools to communicate with AI agents.

Use it when changing or debugging the plugin, its JSON-RPC communication, editor integration, debugger messaging, or game-side features such as screenshots.

It explains how the plugin is organised and how commands travel between the AI agent, the editor, and a running game.

How fernforestgames/mcp-server-godot-editor configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to fernforestgames/mcp-server-godot-editor. 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/fernforestgames/mcp-server-godot-editor/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/fernforestgames/mcp-server-godot-editor

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/fernforestgames/mcp-server-godot-editor/claude-md/github.svg)](https://agentmods.dev/instructions/fernforestgames/mcp-server-godot-editor/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/fernforestgames/mcp-server-godot-editor/claude-md"><img src="https://agentmods.dev/badge/instructions/fernforestgames/mcp-server-godot-editor/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/fernforestgames/mcp-server-godot-editor/claude-md"><img src="https://agentmods.dev/badge/instructions/fernforestgames/mcp-server-godot-editor/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 930 This file is loaded in full into every session.

When invoked 930 The same file — it is already loaded in full.

Security scan A 0 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.

Model	Per session	Once invoked
Fable 5.1	$0.00930	$0.00930
Opus 5	$0.00465	$0.00465
Sonnet 5	$0.00186	$0.00186
Haiku 4.5	$0.00093	$0.00093

Measured 9d ago against content hash 1beebdc25285, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mcp-server-godot-editor CLAUDE.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 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.

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.

CLAUDE.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

This is a Godot 4.5 editor plugin that implements an MCP (Model Context Protocol) server, allowing AI agents to control the Godot editor. The server communicates via JSON-RPC over stdin/stdout.

Architecture

The plugin consists of two communication layers:

Editor Side (runs in the Godot editor process)

plugin.gd - EditorPlugin entry point that initializes the MCP server and debugger plugin
editor_mcp_server.gd - Main MCP server implementation; handles JSON-RPC protocol, reads from stdin, writes to stdout
engine_client.gd - EditorDebuggerPlugin that communicates with running game instances via Godot's debugger messaging system

Game Side (runs in the debugged game process)

engine_server.gd - Autoload node injected into the running game; handles commands like taking screenshots and sends responses back to the editor

Communication Flow

MCP Client <--stdin/stdout--> editor_mcp_server.gd <--EngineDebugger--> engine_server.gd (in game)
                                      |
                                engine_client.gd (debugger plugin)

MCP Tools Exposed

take_screenshot - Captures a screenshot from the running game (requires game to be running)
play_main_scene - Starts the project's main scene
play_scene - Starts a specific scene by path
stop_playing_scene - Stops the currently running scene
synthesize_input - Injects input events into the running game (key, mouse, action, joypad)
click_node - Finds a node by path/unique name/accessibility name and clicks it
hover_node - Finds a node and moves the mouse to it (for hover states, tooltips)

Development Notes

This is a @tool script codebase; editor scripts run in the editor context
The MCP server runs on a separate thread to avoid blocking the editor
Screenshot data is transferred as WebP and base64-encoded for MCP response
The server disables Engine.print_to_stdout to prevent Godot's print statements from corrupting the JSON-RPC stream
Message prefix "mcp" is used for debugger message capture routing (see constants.gd)

Read the full file on GitHub · 78 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.

9d ago First seen · 78 lines · 930 tokens per session scan A 1beebdc25285

Subscribe to this mod's changes

mcp-server-godot-editor CLAUDE.md is an instructions file published in the GitHub repository fernforestgames/mcp-server-godot-editor (5 stars, last pushed 8mo ago), licensed MIT. It adds 930 tokens to every session, about $0.0047 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.

Game development

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

mcp-server-godot-editor: Instructions file for Claude Code