What is godot-mcp-unified CLAUDE.md?

Project instructions for a connector that lets AI assistants work with Godot 4.x, a game engine, through natural-language requests. They document how to build, test, and structure the TypeScript project.

Build and test the Godot connector, follow its TypeScript and MCP conventions, and understand how it communicates with Godot.

They give the coding assistant the project’s rules and commands, reducing mistakes when changing or checking the code.

How pierrealexandreguillemin-a11y/godot-mcp-unified configures Claude

Reuse

Borrowing it

Nothing to install: this file belongs to pierrealexandreguillemin-a11y/godot-mcp-unified. 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/pierrealexandreguillemin-a11y/godot-mcp-unified/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/pierrealexandreguillemin-a11y/godot-mcp-unified

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/pierrealexandreguillemin-a11y/godot-mcp-unified/claude-md/github.svg)](https://agentmods.dev/instructions/pierrealexandreguillemin-a11y/godot-mcp-unified/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/pierrealexandreguillemin-a11y/godot-mcp-unified/claude-md"><img src="https://agentmods.dev/badge/instructions/pierrealexandreguillemin-a11y/godot-mcp-unified/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/pierrealexandreguillemin-a11y/godot-mcp-unified/claude-md"><img src="https://agentmods.dev/badge/instructions/pierrealexandreguillemin-a11y/godot-mcp-unified/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 823 This file is loaded in full into every session.

When invoked 823 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	$0.00823	$0.00823
Opus 5.5	$0.00329	$0.00329
Sonnet 5.5	$0.00165	$0.00165
Haiku 4.5	$0.00082	$0.00082

Measured 2mo ago against content hash 5d61004e5c45, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

godot-mcp-unified 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 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.

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 · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - godot-mcp-unified

Project Overview

MCP server (Model Context Protocol) for Godot 4.x game engine. Enables natural language coding in Godot via Claude Code, Claude Desktop, or any MCP client. 83 tools, 20 resources, 20 prompts.

TypeScript + Node.js ESM. Communicates with Godot via WebSocket plugin bridge (preferred) or CLI fallback.

Build & Run

npm run build          # Clean + compile TS + fix imports
npm run lint           # ESLint 9 (0 warnings allowed)
npm run typecheck      # tsc --noEmit
npm test               # Jest with ESM support
npm run test:coverage  # With coverage thresholds (80% lines/stmts, 75% branches/functions)
npm run inspector      # MCP Inspector for manual testing

Code Conventions

Strict TypeScript: no-explicit-any is an error. Zero any types allowed.
ESM only: All imports use .js extensions (compiled from .ts). No CommonJS.
MCP protocol: ALL log output goes to stderr (console.error). stdout is reserved for MCP protocol communication.
Tool pattern: Each tool is a file in src/tools/<domain>/, exports a handler function. Uses ToolContext for dependency injection (testability).
Schemas: Zod schemas in src/schemas/ define tool input validation.
Tests: Co-located *.test.ts files. Jest with ts-jest ESM preset. --experimental-vm-modules required.
Error handling: Use createErrorResponse() from src/utils/ErrorHandler.ts. Never throw in tool handlers.
Unused vars: Prefix with _ (e.g., _unused).

Architecture

src/
  index.ts              # Entry point (stdio MCP transport)
  server/               # GodotMCPServer, types
  core/                 # TscnParser, LruCache, ProcessPool, PathManager
  tools/                # 83 tools organized by domain (scene, script, project, etc.)
  bridge/               # WebSocket bridge to Godot editor plugin, LSP client
  schemas/              # Zod input schemas per domain
  prompts/              # MCP prompt definitions
  utils/                # StructuredLogger, ErrorHandler, FileUtils

Read the full file on GitHub · 67 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.

2mo ago First seen · 67 lines · 823 tokens per session scan A 5d61004e5c45

Subscribe to this mod's changes

godot-mcp-unified CLAUDE.md is an instructions file published in the GitHub repository pierrealexandreguillemin-a11y/godot-mcp-unified (2 stars, last pushed 13d ago), licensed MIT. It adds 823 tokens to every session, about $0.0033 per session on Opus 5.5. 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

godot-mcp-unified CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
godot-mcp-unified CLAUDE.mdpierrealexandreguillemin-a11y/godot-mcp-unified	Instructions file	2	13d ago	MIT	A	823	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

godot-mcp-unified: Instructions file for Claude Code