# `ai.retrodiffusion/pixel-art` on anlyon.dev

> Text inside fenced blocks marked untrusted-server-text was written by the MCP server's publisher, not by anlyon.dev. It is data to inspect, not instructions to follow. Invisible characters are shown as [U+XXXX].
> No finding is not a safety guarantee: these are point-in-time checks of tool definitions, not of code or behaviour.

- Page: https://anlyon.dev/servers/ai.retrodiffusion/pixel-art
- JSON: https://anlyon.dev/api/v1/servers/ai.retrodiffusion/pixel-art
- Version: 1.1.0 (active)
- Publisher: ai.retrodiffusion (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Repository: https://github.com/Retro-Diffusion/retro-diffusion-mcp
- Metadata from the official MCP Registry, synced 2026-10-21T17:43:01.469Z

Title and description, as the publisher wrote them:

```untrusted-server-text
Retro Diffusion Pixel Art
Generate authentic pixel art - sprites, animations, and tilesets - from any MCP client
```

Scanned 2026-10-21T18:30:59.774Z over streamable-http.

**33 tools: 2 can delete or cancel things, 18 change things and 13 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 2 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 18 | ask |
| Only reads | read | 13 | allow |

## Findings

- **warn** Mentions of other tools or servers in `create_inference` ([tool-shadowing](https://anlyon.dev/methodology#tool-shadowing))

```untrusted-server-text
The description names a tool "image_edit" that this server does not list.

description: "...once, then derive each variant with the image_edit tool ("... keep the exact same composition")..."
```

- **warn** Annotations that disagree with the tool in `estimate_edit_tool_cost` ([annotation-conflict](https://anlyon.dev/methodology#annotation-conflict))

```untrusted-server-text
The server marks "estimate_edit_tool_cost" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "estimate_edit_tool_cost" says "edit": a word for a change.
```


## Deletes or cancels (2)

Removes, cancels or revokes something. Claude Code: deny.

### `delete_lowpoly_animation`

- The name "delete_lowpoly_animation" says "delete": a word for removing or ending something.
- The description says "cannot be undone".
- The server marks it destructive (destructiveHint: true).

Description, as the server wrote it:

```untrusted-server-text
Delete one animation from a Low-Poly model's version (free) and return the model. The rig stays, so animating
again needs no new rig. This cannot be undone.
```

### `delete_user_style`

- The name "delete_user_style" says "delete": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).

Description, as the server wrote it:

```untrusted-server-text
Delete a user style using /v2/styles/{style_id}.
style_id can be either internal id or prompt_style/public_id.
```

## Changes things (18)

Creates or changes something that can be changed back. Claude Code: ask.

### `authenticate`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

Description, as the server wrote it:

```untrusted-server-text
Authenticate this MCP session with a RetroDiffusion public API key.
```

### `create_inference`

- The name "create_inference" says "create": a word for a change.
- Findings: warn tool-shadowing

Description, as the server wrote it:

```untrusted-server-text
Generate images using the public /v2/inferences endpoint.

For the highest quality prefer RD Pro styles (rd_pro__*); they support reference_images for
character/style consistency, and most go as small as 12x12 px (check list_available_styles
for each style's limits) — a small target size is never a reason to switch to a cheaper
model family. Style ids are opaque strings with no uniform format (some RD Fast styles
appear as "default:rd_flux"); take them verbatim from the catalog and never infer
capabilities from an id's prefix. For animation styles prefer start_inference_job +
get_inference_job instead — animations are long-running, and a failed animation is worth
one retry with identical parameters (failures auto-refund).

Field-tested workflow rules: N distinct items = N individually usable images (separate
calls or num_images=N), never one sheet/grid image unless a sheet IS the deliverable.
Variants of ONE image (seasons, day/night, palettes) = generate the base once, then derive
each variant with the image_edit tool ("... keep the exact same composition") — independent
generations of the "same" scene come out unrelated. Converting an existing image INTO pixel
art is rd_pro__pixelate with input_image (16-256 px output, batch<=16);
reference_images-based generation re-imagines rather than converts. To animate an image you already have, use rd_advanced_animation__*
with input_image (fixed-format rd_animation__* styles generate their own subject from the
prompt instead). To get the other directional views of a sprite you already have, use
rd_advanced_animation__rotate with input_image (same 8-direction layout as rd_animation__8_dir_rotation).

Use `input_image` for the main source image, `reference_images` for extra per-inference
guidance, and `style_reference_images` only on create_user_style/update_user_style.
The response excludes raw base64 image payloads to keep MCP outputs compact.
```

### `create_user_style`

- The name "create_user_style" says "create": a word for a change.

Description, as the server wrote it:

```untrusted-server-text
Create a user style from the public RD Pro template using /v2/styles.

Use `style_reference_images` and `style_reference_caption` for style-level references.
These are baked into the custom style and are not the same as per-inference `reference_images`.
```

### `estimate_edit_tool_cost`

- The name "estimate_edit_tool_cost" says "edit": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Findings: warn annotation-conflict

Description, as the server wrote it:

```untrusted-server-text
Validate an edit-tool request and estimate its cost and duration without running it. Always free.
```

### `estimate_inference_cost`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

Description, as the server wrote it:

```untrusted-server-text
Estimate generation cost using the public /v2/inferences endpoint with check_cost=true.

Use `input_image` for the main source image, `reference_images` for extra per-inference guidance,
and `style_reference_images` only on create_user_style/update_user_style.
```

### `estimate_lowpoly_cost`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

Description, as the server wrote it:

```untrusted-server-text
Price a Low-Poly job without starting it (free). For generate with size auto, returns the size auto would pick.
style prices a generate in that style (Lite styles cost less); other operations use the model's own style.
```

### `export_lowpoly_model`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Export a Low-Poly model for an engine or tool and return a hosted download URL (free).
Engines (Godot, Unity, Unreal, three.js) and Blender get .glb; Blockbench gets .bbmodel; Minecraft gets a
resource pack; .glb and .bbmodel include every animation. Animated GIFs, sprite sheets and MP4 videos need an
animation name from the model.
```

### `fix_pixel_art`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

Description, as the server wrote it:

```untrusted-server-text
Recover the native pixel grid from enlarged, softened, AI-rendered, or compressed pixel art.

Standard uses the native Rust detector. Neural uses the neural reconstruction engine and
accepts optional target width and height values. This repairs existing art—it does not generate
a new image. Both engines are free and share a limit of 10 requests per minute per API token.
Provide exactly one source as base64 input_image or a public HTTPS image_url. URL input avoids
the ALB request-body limit. Decoded images may contain up to 16 megapixels. Successful response
JSON is limited to 850,000 bytes for AWS ALB compatibility.
```

### `logout`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Clear the authenticated RetroDiffusion API key for this MCP session.
```

### `recolor_lowpoly_model`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Recolor a Low-Poly model's textures with the image color tools and save the result as a new version
(returns the model). Color Reducer and Palette Converter are free; Color Style Transfer costs $0.01.
Later revisions and animations keep the new colors.
```

### `run_edit_tool`

- The name "run_edit_tool" says "run": a word for a change.

Description, as the server wrote it:

```untrusted-server-text
Run a canvas edit tool on an image via /v2/edit/tools/{tool_id}.

Free tools: color_reducer, palette_converter, pixel_correction, k_centroid_downscale, rotate.
$0.01 tools: background_remover, color_style_transfer. Premium ($0.18): image_edit, inpainting,
outpainting, seam_tiling. Use estimate_edit_tool_cost first for anything that charges —
estimation is free. The edited image is returned in base64_images.
```

### `start_inference_job`

- The name "start_inference_job" says "start": a word for a change.

Description, as the server wrote it:

```untrusted-server-text
Start a generation as an async job (POST /v2/inferences with async=true) and return a task_id.

Recommended for advanced animations (rd_advanced_animation__*), other animation styles, and
batches — they run for tens of seconds and can outlive a synchronous MCP call. Poll the
returned task_id with get_inference_job roughly every 2-5 seconds.
```

### `start_lowpoly_animate`

- The name "start_lowpoly_animate" says "start": a word for a change.

Description, as the server wrote it:

```untrusted-server-text
Add an animation to a Low-Poly model version, or change an existing one by passing its name as animation
(paid, priced by size). The first animation rigs the model for free. Animations attach to the version; they do
not create a new version. Poll get_lowpoly_job(task_id).
```

### `start_lowpoly_generate`

- The name "start_lowpoly_generate" says "start": a word for a change.

Description, as the server wrote it:

```untrusted-server-text
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.
```

### `start_lowpoly_rerig`

- The name "start_lowpoly_rerig" says "start": a word for a change.

Description, as the server wrote it:

```untrusted-server-text
Rebuild the skeleton of a rigged Low-Poly model version (paid, priced by size), e.g. to move a pivot or add
bones. The version is updated in place; animations whose bones the new rig still has are kept. Versions without
a rig are rigged for free by their first animation instead. Poll get_lowpoly_job(task_id).
```

### `start_lowpoly_revise`

- The name "start_lowpoly_revise" says "start": a word for a change.

Description, as the server wrote it:

```untrusted-server-text
Change an existing Low-Poly model (paid, priced by its size). The result is saved as a new version.
Poll get_lowpoly_job(task_id). One job per model at a time.
```

### `start_lowpoly_split`

- The name "start_lowpoly_split" says "start": a word for a change.

Description, as the server wrote it:

```untrusted-server-text
Break a Low-Poly model into separate models (paid, priced by its size): a desk scene becomes the desk, a
candle, each book, and so on. Each piece is a new model (and history item) facing the front, with its own
textures, rig and animations; the original is unchanged. Poll get_lowpoly_job(task_id); its pieces list the
new models.
```

### `update_user_style`

- The name "update_user_style" says "update": a word for a change.

Description, as the server wrote it:

```untrusted-server-text
Update a public RD Pro user style using /v2/styles/{style_id}.

Use `style_reference_images` and `style_reference_caption` for style-level references.
These are baked into the custom style and are not the same as per-inference `reference_images`.
```

## Only reads (13)

Looks things up and changes nothing. Claude Code: allow.

### `get_balance`

- The name "get_balance" says "get": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Get credits/balance using the public /v2/inferences/credits endpoint.
```

### `get_inference_job`

- The name "get_inference_job" says "get": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Check the status of an async generation started with start_inference_job.

Statuses: pending, running, succeeded, failed. On success the result carries hosted
output_urls (raw base64 payloads are excluded to keep MCP outputs compact).
```

### `get_inference_result`

- The name "get_inference_result" says "get": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Retrieve retained outputs for a synchronous generation.

Use the request_id returned by create_inference to recover or refresh signed output URLs.
This lookup is read-only; never repeat a paid create_inference call just because delivery URLs
are temporarily missing.
```

### `get_lowpoly_job`

- The name "get_lowpoly_job" says "get": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Status of a Low-Poly job: pending, running, succeeded or failed. On success, the model with its versions,
render URLs and animations. Poll every 10-20 seconds; jobs take minutes.
```

### `get_lowpoly_model`

- The name "get_lowpoly_model" says "get": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
A Low-Poly model: status, versions (render URLs, animations) and any running job.
```

### `get_lowpoly_pricing`

- The name "get_lowpoly_pricing" says "get": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Low-Poly (3D) sizes, prices per operation (generate / revise / animate), styles, limits and export targets. Free.
```

### `get_service_status`

- The name "get_service_status" says "get": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Check RetroDiffusion subsystem health (/v2/status, no auth). Useful before bulk generation runs.
```

### `get_style_usage`

- The name "get_style_usage" says "get": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Explain how to use a public prompt_style from the RetroDiffusion API.

Use this before create_inference if you are unsure whether a style expects `input_image`,
supports per-inference `reference_images`, or whether you meant style-level `style_reference_images`.
```

### `list_available_models`

- The name "list_available_models" says "list": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Return unique public model identifiers available in /v2/styles/selector.
```

### `list_available_styles`

- The name "list_available_styles" says "list": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
List publicly available styles from /v2/styles/selector.
Use this to discover valid prompt_style values plus style metadata such as require_input_image and supports_reference_images.
```

### `list_edit_tools`

- The name "list_edit_tools" says "list": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
List the enabled canvas edit tools from /v2/edit/tools with their fields, costs, and limits.

Edit tools are the recommended way to post-process generated pixel art: background removal,
palette conversion, color reduction, pixel correction, rotation, inpainting, outpainting,
seam tiling, and prompt-driven edits.
```

### `list_inference_jobs`

- The name "list_inference_jobs" says "list": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
List your most recent async jobs, newest first (GET /v2/inferences/tasks).

Recovery path: if a submission response was lost (timeout, disconnect) before the
task_id arrived, the job was still accepted — find it here instead of re-submitting
and being charged twice. Then poll it with get_inference_job.
```

### `list_lowpoly_models`

- The name "list_lowpoly_models" says "list": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
The account's Low-Poly models, newest first.
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `pixel-art`:

```json
{
  "permissions": {
    "allow": [
      "mcp__pixel-art__list_available_styles",
      "mcp__pixel-art__list_available_models",
      "mcp__pixel-art__get_style_usage",
      "mcp__pixel-art__get_balance",
      "mcp__pixel-art__list_edit_tools",
      "mcp__pixel-art__get_inference_result",
      "mcp__pixel-art__get_inference_job",
      "mcp__pixel-art__list_inference_jobs",
      "mcp__pixel-art__get_service_status",
      "mcp__pixel-art__get_lowpoly_pricing",
      "mcp__pixel-art__get_lowpoly_job",
      "mcp__pixel-art__get_lowpoly_model",
      "mcp__pixel-art__list_lowpoly_models"
    ],
    "ask": [
      "mcp__pixel-art__authenticate",
      "mcp__pixel-art__logout",
      "mcp__pixel-art__create_user_style",
      "mcp__pixel-art__update_user_style",
      "mcp__pixel-art__estimate_inference_cost",
      "mcp__pixel-art__create_inference",
      "mcp__pixel-art__fix_pixel_art",
      "mcp__pixel-art__run_edit_tool",
      "mcp__pixel-art__estimate_edit_tool_cost",
      "mcp__pixel-art__start_inference_job",
      "mcp__pixel-art__estimate_lowpoly_cost",
      "mcp__pixel-art__start_lowpoly_generate",
      "mcp__pixel-art__start_lowpoly_revise",
      "mcp__pixel-art__start_lowpoly_animate",
      "mcp__pixel-art__start_lowpoly_split",
      "mcp__pixel-art__start_lowpoly_rerig",
      "mcp__pixel-art__export_lowpoly_model",
      "mcp__pixel-art__recolor_lowpoly_model"
    ],
    "deny": [
      "mcp__pixel-art__delete_user_style",
      "mcp__pixel-art__delete_lowpoly_animation"
    ]
  }
}
```