ldraw-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LDRAW_MCP_BLENDER | No | Path to the blender binary (overrides PATH lookup) | |
| LDRAW_MCP_DISABLE | No | Set to 1 to force is_available() to False | |
| LDRAW_LIBRARY_PATH | No | Path to the LDraw parts library (community convention) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| check_rendererA | Report whether the LDraw rendering stack is available and why not. |
| render_ldraw_fileA | Render an LDraw model file (.ldr/.mpd/.dat) to a PNG image. Views are rendered at each comma-separated azimuth (degrees) and stitched side by side. Higher samples = cleaner but slower. Bounds: resolution 32..2048 px per view, samples 1..1024, 1..8 azimuths, and resolution^2 x samples x views at most 2**27. A referenced file the LDraw library lacks is left out of the picture and named in a text block after the image. |
| render_ldraw_textA | Render inline LDraw content (the text of a .ldr file) to a PNG. Useful for quick experiments without writing a file first. Same bounds as render_ldraw_file. |
| bill_of_materialsA | Bill of materials for an LDraw model: part x colour x quantity rows. Give |
| lookup_colorA | Look up LDraw colours in the library's LDConfig.ldr.
|
| search_partsA | Search the LDraw library's parts by description or file-name substring. Case-insensitive, runs of spaces collapsed ( |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each tool occupies a clearly distinct niche: rendering (file vs inline text), BOM analysis, colour lookup, part search, and environment diagnostics. The closest pair, render_ldraw_file and render_ldraw_text, is cleanly separated by input form (path vs inline LDraw text) in both name and description. No tool overlaps another's job.
Five of six names follow a consistent snake_case verb_noun pattern (check_renderer, lookup_color, render_ldraw_text, render_ldraw_file, search_parts). bill_of_materials deviates as a bare noun phrase, though it is still immediately readable and unambiguous.
Six tools is well within the sweet spot and each one earns its place: two render entry points, two query tools (parts, colours), one analysis tool, and one diagnostic. Nothing feels padded or redundant for a focused LDraw rendering/inspection server.
The read-only lifecycle is well covered: render a model or raw text, extract a bill of materials, search parts, look up colours, and verify the rendering stack. Minor gaps remain — no model validation/parse-error reporting tool and no way to list library categories or discover models — but agents can work around these.