godot-docs-mcp: Instructions file for Claude Code

CLAUDE.md

godot-docs-mcp CLAUDE.md is an instructions file for Claude Code from mcintalmo/godot-docs-mcp. It costs 1,728 tokens per session, scanned A, original, MIT.

Repository instructions for a local MCP server that provides Godot Engine documentation to AI coding agents. They define its technical rules, project layout, and conventions for adding tools.

In plain words
What is it for?
They are for guiding development of the server, including its Python packages, MCP implementation, and new documentation tools.
Why use it?
They help agents make compatible changes and follow the project's rules for sourcing and serving Godot documentation.

Instructions file for Claude Code

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

This is mcintalmo/godot-docs-mcp's own configuration. It tells Claude Code how to work on godot-docs-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-docs-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mcintalmo/godot-docs-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/mcintalmo/godot-docs-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/mcintalmo/godot-docs-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-docs-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mcintalmo/godot-docs-mcp/claude-md.svg)](https://agentmods.dev/instructions/mcintalmo/godot-docs-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mcintalmo/godot-docs-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/mcintalmo/godot-docs-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,728 This file is loaded in full into every session.
When invoked 1,728 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01728 $0.01728
Opus 5 $0.00864 $0.00864
Sonnet 5 $0.00346 $0.00346
Haiku 4.5 $0.00173 $0.00173

Measured 6d ago against content hash 7fa873e6eac1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

godot-docs-mcp 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 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.

CLAUDE.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

godot-docs-mcp — working notes

An MCP server serving the Godot Engine documentation to AI coding agents. Eventually the core of a Claude Code plugin that also ships skills for Godot development and game-design documents; the MCP server is the current scope.

Non-negotiables

  • MCP spec revision is 2026-07-28. This is a breaking rework of MCP: stateless (no initialize handshake — protocol version and client capabilities ride in _meta per request), no sessions or Mcp-Session-Id, server/discover is mandatory, subscriptions/listen replaces the HTTP GET/SSE stream, all results carry resultType, and list/read results carry ttlMs + cacheScope.
  • Roots, Sampling, and Logging are deprecated in this revision. Do not adopt them. Log to stderr on stdio.
  • Use the official mcp SDK v2 (from mcp.server.mcpserver import MCPServer), not fastmcp — that is a separate package tracking older revisions.
  • Never fetch docs.godotengine.org. It is behind a Cloudflare JS challenge that returns HTTP 429 to non-browser clients. All content comes from GitHub.

Layer map

Feature-sliced packages under src/godot_docs_mcp/. Dependencies point downward only.

cli.py                  entrypoint: serve / sync / status / search (Typer)
server/                 MCP surface — app.py, tools.py, resources.py
search/                 service.py (orchestration, dedup, budgeting), query.py (query policy)
indexing/               base.py (SearchIndex Protocol), sqlite_fts.py, build.py
parsing/                bbcode.py, class_xml.py, rst.py
sources/                github.py (acquisition + publishing), manifest.py (version pinning),
                        updates.py (cached, non-blocking staleness check)
config.py  models.py  errors.py  text.py    foundation — no I/O in models.py
```text

`indexing/base.py` defines the `SearchIndex` Protocol. **Everything above `indexing/`
depends on that Protocol, never on `sqlite_fts` directly** — that is the seam where a
vector/hybrid index drops in later without touching tool code. Tests are held to it too:
if a test needs something the Protocol does not expose, it takes the concrete index as its
own fixture rather than reaching through the seam.

Read the full file on GitHub · 116 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. 6d ago First seen · 116 lines · 1,728 tokens per session scan A 7fa873e6eac1

Subscribe to this mod's changes

godot-docs-mcp CLAUDE.md is an instructions file published in the GitHub repository mcintalmo/godot-docs-mcp (0 stars, last pushed 16d ago), licensed MIT. It adds 1,728 tokens to every session, about $0.0086 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.

Related

Other instructions, from other repositories

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 · 5,182 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

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

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

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

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