brick-mcp-app CLAUDE.md

brick-mcp-app CLAUDE.md is an instructions file for coding agents from dend/brick-mcp-app. It costs 389 tokens per session, scanned A, original, MIT.

Instructions for a Three.js brick-building app that lets users design 3D constructions through an MCP-enabled host. The server stores the shared scene state, while a React and Three.js client displays it.

In plain words
What is it for?
Use it when building or changing the MCP server, 3D client, scene-state handling, build process, or brick-parts setup.
Why use it?
It gives developers the project’s naming rules, architecture, specifications, technology choices, and commands in one place.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/dend/brick-mcp-app/claude-md
Clone the repo
git clone --depth 1 https://github.com/dend/brick-mcp-app

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 brick-mcp-app CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dend/brick-mcp-app/claude-md.svg)](https://agentmods.dev/instructions/dend/brick-mcp-app/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dend/brick-mcp-app/claude-md"><img src="https://agentmods.dev/badge/instructions/dend/brick-mcp-app/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 389 This file is loaded in full into every session.
When invoked 389 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00389 $0.00389
Opus 5 $0.00195 $0.00195
Sonnet 5 $0.00078 $0.00078
Haiku 4.5 $0.00039 $0.00039

Measured 5d ago against content hash 57ac1bf5d826, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

brick-mcp-app 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 5d 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 · 38 lines

What it actually says

Brick Builder MCP App

A Three.js MCP App for designing 3D brick constructions inside MCP-enabled hosts like Claude Desktop.

Important rules

  • Never use the term "LEGO" anywhere in the codebase, comments, documentation, or UI text. Use "brick" or "brick builder" instead.
  • Server is the source of truth for scene state. Both LLM and UI mutate state through MCP tools.

Specs

Project specifications live in specs/. Read these before making architectural decisions:

  • specs/0001-initial-spec/spec.md — Full initial specification (architecture, types, tools, build config, implementation phases)

Tech stack

  • Server: TypeScript, Express, @modelcontextprotocol/sdk, @modelcontextprotocol/ext-apps
  • Client: React, Three.js, bundled as single HTML via Vite + vite-plugin-singlefile
  • Runtime: tsx for dev, esbuild for production builds

Key commands

npm install          # Install dependencies
npm run download:ldraw # One-time: download LDraw parts library
npm run build        # Build client + server
npm run serve        # Start server (dev mode with tsx)
npm run dev          # Watch + serve concurrently

Architecture

  • Scene state is module-level (shared across MCP sessions) — the host creates separate sessions for LLM and app iframe
  • The UI polls brick_get_scene every 1s to pick up LLM-initiated changes
  • brick_place returns footprint data ({minX, maxX, minZ, maxZ, topY}) so the LLM can position bricks precisely
  • Only brick_render_scene has resourceUri — all other model tools use plain server.registerTool to avoid iframe reloads
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. 5d ago First seen · 38 lines · 389 tokens per session scan A 57ac1bf5d826

Subscribe to this mod's changes

brick-mcp-app CLAUDE.md is an instructions file published in the GitHub repository dend/brick-mcp-app (23 stars, last pushed 5mo ago), licensed MIT. It adds 389 tokens to every session, about $0.0019 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 2026-08-30.