ldraw-mcp
Renders LEGO LDraw model files (.ldr, .mpd, .dat) to high-quality images using headless Blender, enabling MCP clients to visually inspect LEGO builds.
README
<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.
<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
# 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); 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 pointLDRAW_MCP_BLENDERat the binary. Install it yourself (package manager, blender.org, or a local build);ldraw-mcp-setupdoes not install Blender. - ImportLDraw addon (
io_scene_importldraw) in Blender's addons dir — installed byldraw-mcp-setup. - LDraw parts library at
~/.ldraw(orLDRAW_LIBRARY_PATH) — installed byldraw-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
and unzip so that
~/.ldraw/parts/exists. - ImportLDraw addon: download the latest release from
TobyLobster/ImportLDraw
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_renderersays NOT FOUND: runldraw-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_importldrawin 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.
<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>
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。