MCP server that renders LDraw/LEGO models to images with real part geometry (studs, glass, tires) via headless Blender + ImportLDraw — gives vision-capable models eyes for brick builds.
claude mcp add ldraw-mcp -- python -m ldraw-mcp{
"mcpServers": {
"ldraw-mcp": {
"command": "python",
"args": ["-m", "ldraw-mcp"]
}
}
}Resumen de MCP Servers
<div align="center"> # ldraw-mcp **Give your MCP client eyes for LEGO® models.** Render LDraw files (`.ldr` / `.mpd` / `.dat`) to images with *real part geometry* — studs, slopes, window glass — using headless Blender and the ImportLDraw addon. The output looks like a BrickLink Stud.io render, with no GUI anywhere in the loop. [](https://pypi.org/project/ldraw-mcp/) [](https://pypi.org/project/ldraw-mcp/) [](LICENSE) [](https://modelcontextprotocol.io) [](https://github.com/musharna/ldraw-mcp/actions/workflows/ci.yml) <img src="docs/hero.png" alt="Two rendered views of a red LEGO car — real studs, transparent glass, rubber tires, steering wheel" width="100%"> <sub>A ~90-line <code>.ldr</code> rendered front-left and rear-right — actual bricks, not a geometric proxy.</sub> </div> <!-- mcp-name: io.github.musharna/ldraw-mcp --> --- Point a vision-capable model at a build and it sees the actual bricks: crossed rotation matrices, floating plates, sunken windows — the kinds of export bugs a geometric proxy render will happily hide. ## Quickstart ```bash # 1. install pip install ldraw-mcp # 2. install the LDraw parts library + ImportLDraw addon ldraw-mcp-setup # 3. register with Claude Code claude mcp add ldraw -- ldraw-mcp ``` Then ask things like *"render output/build.ldr and tell me what looks wrong"* — the model sees the render, not just the text. > **Blender is a prerequisite** (see [Requirements](#requirements)); it is > not installed by `ldraw-mcp-setup`. ## Tools | tool | what it does | |---|---| | `render_ldraw_file(path, azimuths="-60,120", resolution=640, samples=24)` | Render a model file to a PNG (multi-view, stitched side by side) | | `render_ldraw_text(ldr, azimuths="-60,120", resolution=640, samples=24)` | Render inline LDraw content without writing a file first | | `check_renderer()` | Diagnose the Blender / addon / parts-library setup | `azimuths` is a comma-separated list of view angles in degrees; each is rendered and the views are stitched horizontally. Elevation is fixed at 22°. Higher `samples` = cleaner but slower. ## Requirements - **Blender 4.x** on `PATH`, or point `LDRAW_MCP_BLENDER` at the binary. Install it yourself (package manager, blender.org, or a local build); `ldraw-mcp-setup` does not install Blender. - **ImportLDraw addon** (`io_scene_importldraw`) in Blender's addons dir — installed by `ldraw-mcp-setup`. - **LDraw parts library** at `~/.ldraw` (or `LDRAW_LIBRARY_PATH`) — installed by `ldraw-mcp-setup`. ### Environment variables | var | meaning | |---|---| | `LDRAW_MCP_BLENDER` | Path to the blender binary (overrides `PATH` lookup) | | `LDRAW_MCP_DISABLE` | Set to `1` to force `is_available()` to `False` | | `LDRAW_LIBRARY_PATH` | Path to the LDraw parts library (community convention) | ### Manual setup If `ldraw-mcp-setup` can't detect things automatically: - **LDraw library:** download [complete.zip](https://library.ldraw.org/library/updates/complete.zip) and unzip so that `~/.ldraw/parts/` exists. - **ImportLDraw addon:** download the latest release from [TobyLobster/ImportLDraw](https://github.com/TobyLobster/ImportLDraw/releases) and install it via *Blender > Preferences > Add-ons > Install*, or unzip into `~/.config/blender/<version>/scripts/addons/io_scene_importldraw/`. (Launch Blender once first so the config directory exists.) ## Troubleshooting - **`check_renderer` says NOT FOUND:** run `ldraw-mcp-setup`, or set the relevant env var above. - **No GPU / WSL2 / containers:** rendering uses **Cycles on CPU**, which works headless everywhere — no GPU or display needed. A ~150-part model takes a few seconds at the default 640px / 24 samples. - **"no mesh objects imported":** the addon couldn't resolve parts — usually a wrong or incomplete LDraw library path. Re-run setup or check `LDRAW_LIBRARY_PATH`. - **Addon not enabled:** the render script enables it automatically per run; if a manual Blender session complains, enable `io_scene_importldraw` in Preferences > Add-ons. ## Provenance This renderer was extracted from the **prompt2brick** project, where it started life as the vision critic's "see the actual model" path. prompt2brick keeps its own vendored copy of the render wrapper and Blender script, but **this repo is the canonical source going forward** — fixes and improvements to the renderer should land here first and be ported back into prompt2brick. ## License MIT — see [LICENSE](LICENSE). --- <sub>LEGO® is a trademark of the LEGO Group, which does not sponsor, authorize, or endorse this project. This tool is not affiliated with the LEGO Group, BrickLink, or the LDraw.org organization.</sub>
Lo que la gente pregunta sobre ldraw-mcp
¿Qué es musharna/ldraw-mcp?
+
musharna/ldraw-mcp es mcp servers para el ecosistema de Claude AI. MCP server that renders LDraw/LEGO models to images with real part geometry (studs, glass, tires) via headless Blender + ImportLDraw — gives vision-capable models eyes for brick builds. Tiene 1 estrellas en GitHub y se actualizó por última vez today.
¿Cómo se instala ldraw-mcp?
+
Puedes instalar ldraw-mcp clonando el repositorio (https://github.com/musharna/ldraw-mcp) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.
¿Es seguro usar musharna/ldraw-mcp?
+
musharna/ldraw-mcp aún no ha sido auditado por nuestro agente de seguridad. Revisa el repositorio original en GitHub antes de usarlo en producción.
¿Quién mantiene musharna/ldraw-mcp?
+
musharna/ldraw-mcp es mantenido por musharna. La última actividad registrada en GitHub es de today, con 0 issues abiertos.
¿Hay alternativas a ldraw-mcp?
+
Sí. En ClaudeWave puedes explorar mcp servers similares en /categories/mcp, ordenados por popularidad o actividad reciente.
Despliega ldraw-mcp en tu cloud
Lleva este repo a producción en minutos. Cada plataforma genera su propio entorno con variables de entorno editables.
¿Mantienes este repo? Añade un badge a tu README
Pega el badge en tu README de GitHub para mostrar que está auditado por ClaudeWave. Cada badge enlaza de vuelta a esta página y muestra el Trust Score actual.
[](https://claudewave.com/repo/musharna-ldraw-mcp)<a href="https://claudewave.com/repo/musharna-ldraw-mcp"><img src="https://claudewave.com/api/badge/musharna-ldraw-mcp" alt="Featured on ClaudeWave: musharna/ldraw-mcp" width="320" height="64" /></a>Más MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
The fastest path to AI-powered full stack observability, even for lean teams.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!