Skip to main content
Glama

Retro Diffusion Pixel Art MCP

by ai.retrodiffusion.mcp
OverviewDiscussionsAdmin

Start Low-Poly 3D Model

start_lowpoly_generate

Start building a low-poly 3D model with pixel-art textures from a prompt and/or reference images (paid). reference_models puts your existing models (by asset_id) into it exactly, e.g. "a tavern with my table". Optional input_palette (a palette image, as for create_inference): the model uses only its colors, and revisions and animations keep them.

Returns task_id and asset_id immediately; poll get_lowpoly_job(task_id) until it succeeds (usually 1-5 minutes). Then use export_lowpoly_model for .glb/.bbmodel/Minecraft/OBJ files, start_lowpoly_revise to change it, or start_lowpoly_animate to add motion. Failed jobs are refunded automatically; never restart a running job.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNoOmit (auto) to let the service pick: quality, or fast for simple requests. "quality" or "fast" to choose. Same price.
sizeNoCube size in texels: "16", "32", "64", "128", "256", or "auto" (default). Auto reads the prompt; reference-image-only requests default to 64. Bigger sizes cost more (see get_lowpoly_pricing).
styleNoLow-Poly style id: rd_lowpoly__detailed (default, free-form shapes), rd_lowpoly__blocky (boxes only, tilted where needed, Minecraft-like), their Lite versions rd_lowpoly__detailed_lite / rd_lowpoly__blocky_lite (a lighter model: simpler results for much less, and Lite prices for everything done to the model later), or another style listed by get_lowpoly_pricing (each style lists its prices).
promptNoWhat to build or change, up to 250 characters.
rd_api_keyNoRetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.
input_paletteNoBase64 image of a color palette; output colors are constrained to it.
idempotency_keyNoOptional retry key: repeating a start call with the same key returns the same job instead of charging again.
reference_imagesNoUp to 4 base64 reference images (PNG/JPEG/WEBP) of the object, e.g. front and side views.
reference_modelsNoasset_ids of your own finished Low-Poly models to build in: each is placed exactly (same shapes and textures) where the prompt puts it, or adapted. Images and models together: at most 4.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / style / description
      Previous value: -"Low-Poly style id: rd_lowpoly__detailed (default, free-form shapes), rd_lowpoly__blocky (boxes only, tilted where needed, Minecraft-like), or another style listed by get_lowpoly_pricing."New value: +"Low-Poly style id: rd_lowpoly__detailed (default, free-form shapes), rd_lowpoly__blocky (boxes only, tilted where needed, Minecraft-like), their Lite versions rd_lowpoly__detailed_lite / rd_lowpoly__blocky_lite (a lighter model: simpler results for much less, and Lite prices for everything done to the model later), or another style listed by get_lowpoly_pricing (each style lists its prices)."
  2. Changed1 schema field changed
    • addedInput schema / properties / reference_models
      Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "asset_ids of your own finished Low-Poly models to build in: each is placed exactly (same shapes and textures) where the prompt puts it, or adapted. Images and models together: at most 4."
+}
  3. Changed1 schema field changed
    • changedInput schema / properties / mode / description
      Previous value: -"\"quality\" (default) or \"fast\" (quicker, simpler shapes). Same price."New value: +"Omit (auto) to let the service pick: quality, or fast for simple requests. \"quality\" or \"fast\" to choose. Same price."
  4. Changed1 schema field changed
    • addedInput schema / properties / input_palette
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Base64 image of a color palette; output colors are constrained to it."
+}
  5. Changed1 schema field changed
    • changedInput schema / properties / style / description
      Previous value: -"Low-Poly style id: rd_lowpoly__detailed (default, free-form shapes), rd_lowpoly__blocky (boxes only, Minecraft-like), or another style listed by get_lowpoly_pricing."New value: +"Low-Poly style id: rd_lowpoly__detailed (default, free-form shapes), rd_lowpoly__blocky (boxes only, tilted where needed, Minecraft-like), or another style listed by get_lowpoly_pricing."
  6. Added

TDQS

A4.8/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (readOnlyHint=false, idempotentHint=false, destructiveHint=false), the description reveals the async behavior ('Returns task_id and asset_id immediately'), the refund policy ('Failed jobs are refunded automatically'), and the constraint on restarting jobs. It also explains that input_palette colors persist into revisions and animations. These are critical behavioral traits that the annotations do not capture.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single dense paragraph that is front-loaded with the main purpose. It packs a lot of information but is reasonably organized: it starts with the core action, then explains key parameters, then the return and follow-up workflow, then the refund/restart caveat. It could benefit from line breaks or bullet points for clarity, but every sentence adds value and there is no fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex tool with 9 optional parameters and no required inputs, the description covers the full workflow: what to provide, what is returned, how to poll, what to do next, and failure handling. It also mentions the cost implication ('paid') and the pricing nuance for size in the schema. The agent has enough information to invoke the tool correctly and know the expected outcome, including the asynchronous nature.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already covers all parameters with 100% description coverage, so the baseline is 3. The description adds meaningful semantics for reference_models ('puts your existing models (by asset_id) into it exactly') and input_palette ('the model uses only its colors, and revisions and animations keep them'), which go beyond the schema's terse descriptions. It does not add semantics for mode, size, style, or idempotency_key, but the schema descriptions are already detailed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: 'Start building a low-poly 3D model with pixel-art textures from a prompt and/or reference images.' It names the resource (low-poly 3D model), the verb (start building), and the input types. It also distinguishes itself from sibling tools by naming export_lowpoly_model, start_lowpoly_revise, and start_lowpoly_animate as subsequent steps, preventing confusion with them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit workflow guidance: it says to poll get_lowpoly_job(task_id) until success, then use export_lowpoly_model, start_lowpoly_revise, or start_lowpoly_animate for follow-ups. It also warns 'never restart a running job' and clarifies that reference_models places existing models exactly, which implies this tool is for building new models or incorporating existing ones. This gives clear when-to-use and when-not-to-use context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Retro Diffusion Pixel Art MCP toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources