# Retro Diffusion Pixel Art (remote · mcp.retrodiffusion.ai)

Generate authentic pixel art - sprites, animations, and tilesets - from any MCP client

- Trust score: 62/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.retrodiffusion.ai`: 62/100 (this document), [markdown](https://verifymcp.io/servers/ai-retrodiffusion-pixel-art/mcp.md), [page](https://verifymcp.io/servers/ai-retrodiffusion-pixel-art/mcp)

## Channel facts

- Endpoint: `https://mcp.retrodiffusion.ai/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (delete_user_style).
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 53/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 5737 tokens (~286/item across 20 items; 20 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http ai-retrodiffusion-pixel-art https://mcp.retrodiffusion.ai/mcp
```

### Codex

```toml
[mcp_servers.ai-retrodiffusion-pixel-art]
url = "https://mcp.retrodiffusion.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-retrodiffusion-pixel-art": {
      "type": "remote",
      "url": "https://mcp.retrodiffusion.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-retrodiffusion-pixel-art --url https://mcp.retrodiffusion.ai/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-retrodiffusion-pixel-art:
    url: "https://mcp.retrodiffusion.ai/mcp"
```

### Other

```json
{
  "mcpServers": {
    "ai-retrodiffusion-pixel-art": {
      "type": "http",
      "url": "https://mcp.retrodiffusion.ai/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 62, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional] New tool “get_inference_result”

### 2026-08-02 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 61, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 60, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 60, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-28 (score 59, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 58, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 58)

First indexed and scored.

## MCP tools (20)

### `authenticate` (~51 tokens)

Authenticate

Authenticate this MCP session with a RetroDiffusion public API key.

Input parameters:

- `api_key` (string, required): RetroDiffusion API key (rdpk-...), created free at https://retrodiffusion.ai/app/devtools.

### `logout` (~20 tokens)

Log Out

Clear the authenticated RetroDiffusion API key for this MCP session.

### `create_user_style` (~371 tokens)

Create Custom Style

Create a user style from the public RD Pro template using /v1/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`.

Input parameters:

- `apply_prompt_fixer`: Let the API tidy prompts automatically for this style (default true).
- `description`: Short description of the custom style.
- `expanded_llm_instructions`: Extended instructions for the prompt-expansion LLM.
- `force_bg_removal`: Always remove backgrounds for this style.
- `force_palette`: Always apply palette constraining for this style.
- `llm_instructions`: Instructions for the prompt-expansion LLM when this style is used.
- `min_height`: Force a fixed height (96-256); must be provided together with min_width.
- `min_width`: Force a fixed width (96-256); must be provided together with min_height.
- `name` (string, required): Display name for the custom style.
- `rd_api_key`: RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.
- `reference_caption`: Alias for style_reference_caption on this tool; prefer style_reference_caption and never provide both.
- `reference_images`: Alias for style_reference_images on this tool; prefer style_reference_images and never provide both.
- `style_icon`: Icon name for the style (e.g. 'sparkles').
- `style_reference_caption`: Caption describing the style reference image(s).
- `style_reference_images`: Style-level reference image(s), base64, baked into the custom style (max 1 via the public API).
- `user_prompt_template`: Prompt template for the style; must contain the {prompt} token.

### `update_user_style` (~425 tokens)

Update Custom Style

Update a public RD Pro user style using /v1/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`.

Input parameters:

- `apply_prompt_fixer`: Let the API tidy prompts automatically for this style (default true).
- `description`: Short description of the custom style.
- `expanded_llm_instructions`: Extended instructions for the prompt-expansion LLM.
- `force_bg_removal`: Always remove backgrounds for this style.
- `force_palette`: Always apply palette constraining for this style.
- `llm_instructions`: Instructions for the prompt-expansion LLM when this style is used.
- `min_height`: Force a fixed height (96-256); must be provided together with min_width.
- `min_width`: Force a fixed width (96-256); must be provided together with min_height.
- `name`: New display name for the custom style.
- `rd_api_key`: RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.
- `reference_caption`: Alias for style_reference_caption on this tool; prefer style_reference_caption and never provide both.
- `reference_images`: Alias for style_reference_images on this tool; prefer style_reference_images and never provide both.
- `reset_forced_dimensions` (boolean): Clear previously forced dimensions; do not combine with min_width/min_height.
- `style_icon`: Icon name for the style (e.g. 'sparkles').
- `style_id` (string, required): Style id — the internal id or the prompt_style/public id (e.g. user__mystyle_ab12).
- `style_reference_caption`: Caption describing the style reference image(s).
- `style_reference_images`: Style-level reference image(s), base64, baked into the custom style (max 1 via the public API).
- `user_prompt_template`: Prompt template for the style; must contain the {prompt} token.

### `delete_user_style` (~93 tokens)

Delete Custom Style

Delete a user style using /v1/styles/{style_id}.
style_id can be either internal id or prompt_style/public_id.

Input parameters:

- `rd_api_key`: RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.
- `style_id` (string, required): Style id — the internal id or the prompt_style/public id (e.g. user__mystyle_ab12).

### `list_available_styles` (~119 tokens)

List Styles

List publicly available styles from /v1/styles/selector.
Use this to discover valid prompt_style values plus style metadata such as require_input_image and supports_reference_images.

Input parameters:

- `model`: Filter styles by model: rd_fast, rd_plus, rd_pro, or rd_mini.
- `rd_api_key`: RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.
- `tab`: Filter styles by tab: tab:image, tab:animation, tab:advanced-animation, or tab:tileset.

### `list_available_models` (~50 tokens)

List Models

Return unique public model identifiers available in /v1/styles/selector.

Input parameters:

- `rd_api_key`: RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.

### `get_style_usage` (~127 tokens)

Get Style Usage

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`.

Input parameters:

- `prompt_style` (string, required): Style id from list_available_styles (e.g. 'rd_fast__default', 'rd_pro__isometric', or a custom 'user__...' style).
- `rd_api_key`: RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.

### `get_balance` (~51 tokens)

Get Balance

Get credits/balance using the public /v1/inferences/credits endpoint.

Input parameters:

- `rd_api_key`: RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.

### `estimate_inference_cost` (~600 tokens)

Estimate Cost (Free)

Estimate generation cost using the public /v1/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.

Input parameters:

- `bypass_prompt_expansion`: Skip the automatic LLM prompt enrichment and use the prompt verbatim.
- `extra_input_image`: Second base64 input image for styles that use one (e.g. the second texture in rd_tile__tileset_advanced).
- `extra_prompt`: Secondary prompt for styles that use one (e.g. the transition texture in advanced tilesets).
- `frames_duration`: Animation frame count for animation styles: 4, 6, 8, 10, 12, or 16.
- `height` (integer, required): Output height in pixels. Each style enforces its own limits; check list_available_styles or get_style_usage.
- `include_downloadable_data`: Include extra structured assets when available (e.g. tileset atlas JSON, animation frame data).
- `input_image`: Base64 PNG used as the main source image for edits, variations, tilesets, animations, or styles that require a starting frame. Raw base64 or a data URL.
- `input_palette`: Base64 image of a color palette; output colors are constrained to it.
- `num_images` (integer): How many images to generate in one batch. Style-specific maximums apply.
- `prompt` (string, required): Describe the SUBJECT only (e.g. 'a knight resting by a campfire'). Never write 'pixel art' — the selected style handles all rendering.
- `prompt_style` (string, required): Style id from list_available_styles (e.g. 'rd_fast__default', 'rd_pro__isometric', or a custom 'user__...' style).
- `rd_api_key`: RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.
- `reference_images`: Extra per-inference guidance images (base64), only for styles where supports_reference_images is true. Not for defining custom styles.
- `return_non_bg_removed`: Also return the render from before background removal was applied.
- `return_pre_palette`: Also return the render from before palette constraints were applied.
- `return_spritesheet`: For animation styles: return a PNG sprite sheet instead of a GIF.
- `strength`: How strongly to change input_image, 0-1 (default 0.75). Lower values keep more of the original.
- `timeout_seconds`: Read-timeout override in seconds for this call; increase for animations or large batches.
- `upscale_output_factor`: Integer upscale factor for the output image; 1 returns the native pixel size.
- `width` (integer, required): Output width in pixels. Each style enforces its own limits; check list_available_styles or get_style_usage.

### `create_inference` (~752 tokens)

Generate Pixel Art

Generate images using the public /v1/inferences endpoint.

For the highest quality prefer RD Pro styles (rd_pro__*); they support reference_images for
character/style consistency. For animation styles prefer start_inference_job + get_inference_job
instead — animations are long-running. 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.

Input parameters:

- `bypass_prompt_expansion`: Skip the automatic LLM prompt enrichment and use the prompt verbatim.
- `extra_input_image`: Second base64 input image for styles that use one (e.g. the second texture in rd_tile__tileset_advanced).
- `extra_prompt`: Secondary prompt for styles that use one (e.g. the transition texture in advanced tilesets).
- `frames_duration`: Animation frame count for animation styles: 4, 6, 8, 10, 12, or 16.
- `height` (integer, required): Output height in pixels. Each style enforces its own limits; check list_available_styles or get_style_usage.
- `include_downloadable_data`: Include extra structured assets when available (e.g. tileset atlas JSON, animation frame data).
- `input_image`: Base64 PNG used as the main source image for edits, variations, tilesets, animations, or styles that require a starting frame. Raw base64 or a data URL.
- `input_palette`: Base64 image of a color palette; output colors are constrained to it.
- `num_images` (integer): How many images to generate in one batch. Style-specific maximums apply.
- `prompt` (string, required): Describe the SUBJECT only (e.g. 'a knight resting by a campfire'). Never write 'pixel art' — the selected style handles all rendering.
- `prompt_style` (string, required): Style id from list_available_styles (e.g. 'rd_fast__default', 'rd_pro__isometric', or a custom 'user__...' style).
- `rd_api_key`: RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.
- `reference_images`: Extra per-inference guidance images (base64), only for styles where supports_reference_images is true. Not for defining custom styles.
- `remove_bg` (boolean): Remove the background for transparent output.
- `return_non_bg_removed`: Also return the render from before background removal was applied.
- `return_pre_palette`: Also return the render from before palette constraints were applied.
- `return_spritesheet`: For animation styles: return a PNG sprite sheet instead of a GIF.
- `seed`: Seed for reproducible results; reuse the same seed to iterate on one composition.
- `strength`: How strongly to change input_image, 0-1 (default 0.75). Lower values keep more of the original.
- `tile_x` (boolean): Make the result tile seamlessly on the horizontal axis.
- `tile_y` (boolean): Make the result tile seamlessly on the vertical axis.
- `timeout_seconds`: Read-timeout override in seconds for this call; increase for animations or large batches.
- `upload_outputs` (boolean): Host outputs and return URLs in output_urls (recommended for MCP clients) instead of only base64 payloads.
- `upscale_output_factor`: Integer upscale factor for the output image; 1 returns the native pixel size.
- `width` (integer, required): Output width in pixels. Each style enforces its own limits; check list_available_styles or get_style_usage.

### `list_edit_tools` (~100 tokens)

List Edit Tools

List the enabled canvas edit tools from /v1/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.

Input parameters:

- `rd_api_key`: RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.

### `fix_pixel_art` (~353 tokens)

Fix Pixel Art

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.

Input parameters:

- `engine` (string): Fixer engine. Standard uses the native Rust detector; neural uses the neural reconstruction engine.
- `height`: Optional neural target dimension in pixels. Accepted only with engine='neural'.
- `image_url`: Public HTTPS PNG or JPEG URL to reconstruct. Provide this or input_image, not both. URL downloads may contain up to 20 MB and bypass the API request-body limit.
- `input_image`: Base64 PNG or JPEG to reconstruct at its native pixel grid. Raw base64 or a data URL; provide this or image_url, not both. Decoded input may contain up to 16 megapixels, and complete base64 request J…
- `rd_api_key`: RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.
- `timeout_seconds`: Read-timeout override in seconds for this call; increase for animations or large batches.
- `width`: Optional neural target dimension in pixels. Accepted only with engine='neural'.

### `run_edit_tool` (~678 tokens)

Run Edit Tool

Run a canvas edit tool on an image via /v1/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.

Input parameters:

- `color_count`: color_reducer: target number of colors.
- `dither_mode`: color_reducer/palette_converter: dithering mode.
- `dither_strength`: color_reducer/palette_converter: dithering strength.
- `expand_bottom`: Outpainting: pixels to add on the bottom edge.
- `expand_left`: Outpainting: pixels to add on the left edge.
- `expand_right`: Outpainting: pixels to add on the right edge.
- `expand_top`: Outpainting: pixels to add on the top edge.
- `extra_input_image`: Second base64 input image for styles that use one (e.g. the second texture in rd_tile__tileset_advanced).
- `force_solid_pixels`: background_remover: force fully solid or fully transparent pixels (tool default applies when omitted).
- `height`: k_centroid_downscale: target height in pixels (required for that tool).
- `input_image` (string, required): Base64 PNG of the image to edit (raw base64 or a data URL). Required by every edit tool.
- `input_palette`: Base64 image of a color palette; output colors are constrained to it.
- `mask_image`: Base64 mask for inpainting: white pixels are regenerated, black pixels are kept.
- `prompt`: What to generate or change (required by image_edit and inpainting; optional for outpainting).
- `rd_api_key`: RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.
- `repair_window_size`: seam_tiling: size of the repair window.
- `rotation_degrees`: rotate: rotation angle in degrees (clean-edge pixel rotation).
- `seam_width`: seam_tiling: width in pixels of the seam band to repair.
- `seed`: Seed for reproducible results; reuse the same seed to iterate on one composition.
- `soft_inpaint`: Inpainting/outpainting: blend edits softly with the surrounding pixels.
- `tile_x`: seam_tiling: repair the horizontal seam (tool default applies when omitted).
- `tile_y`: seam_tiling: repair the vertical seam (tool default applies when omitted).
- `timeout_seconds`: Read-timeout override in seconds for this call; increase for animations or large batches.
- `tool_id` (string, required): Edit tool id. One of: image_edit, inpainting, outpainting, seam_tiling, background_remover, color_style_transfer, color_reducer, palette_converter, pixel_correction, k_centroid_downscale, rotate. Use…
- `transparency_threshold`: background_remover: alpha threshold for treating pixels as transparent.
- `width`: k_centroid_downscale: target width in pixels (required for that tool).

### `estimate_edit_tool_cost` (~577 tokens)

Estimate Edit Cost (Free)

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

Input parameters:

- `color_count`: color_reducer: target number of colors.
- `dither_mode`: color_reducer/palette_converter: dithering mode.
- `dither_strength`: color_reducer/palette_converter: dithering strength.
- `expand_bottom`: Outpainting: pixels to add on the bottom edge.
- `expand_left`: Outpainting: pixels to add on the left edge.
- `expand_right`: Outpainting: pixels to add on the right edge.
- `expand_top`: Outpainting: pixels to add on the top edge.
- `extra_input_image`: Second base64 input image for styles that use one (e.g. the second texture in rd_tile__tileset_advanced).
- `force_solid_pixels`: background_remover: force fully solid or fully transparent pixels (tool default applies when omitted).
- `height`: k_centroid_downscale: target height in pixels (required for that tool).
- `input_image` (string, required): Base64 PNG of the image to edit (raw base64 or a data URL). Required by every edit tool.
- `input_palette`: Base64 image of a color palette; output colors are constrained to it.
- `mask_image`: Base64 mask for inpainting: white pixels are regenerated, black pixels are kept.
- `prompt`: What to generate or change (required by image_edit and inpainting; optional for outpainting).
- `rd_api_key`: RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.
- `repair_window_size`: seam_tiling: size of the repair window.
- `rotation_degrees`: rotate: rotation angle in degrees (clean-edge pixel rotation).
- `seam_width`: seam_tiling: width in pixels of the seam band to repair.
- `soft_inpaint`: Inpainting/outpainting: blend edits softly with the surrounding pixels.
- `tile_x`: seam_tiling: repair the horizontal seam (tool default applies when omitted).
- `tile_y`: seam_tiling: repair the vertical seam (tool default applies when omitted).
- `timeout_seconds`: Read-timeout override in seconds for this call; increase for animations or large batches.
- `tool_id` (string, required): Edit tool id. One of: image_edit, inpainting, outpainting, seam_tiling, background_remover, color_style_transfer, color_reducer, palette_converter, pixel_correction, k_centroid_downscale, rotate. Use…
- `transparency_threshold`: background_remover: alpha threshold for treating pixels as transparent.
- `width`: k_centroid_downscale: target width in pixels (required for that tool).

### `get_inference_result` (~102 tokens)

Get Generated Outputs

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.

Input parameters:

- `rd_api_key`: RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.
- `request_id` (string, required): Inference request id returned by create_inference.

### `start_inference_job` (~722 tokens)

Start Async Generation

Start a generation as an async job (POST /v1/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.

Input parameters:

- `bypass_prompt_expansion`: Skip the automatic LLM prompt enrichment and use the prompt verbatim.
- `extra_input_image`: Second base64 input image for styles that use one (e.g. the second texture in rd_tile__tileset_advanced).
- `extra_prompt`: Secondary prompt for styles that use one (e.g. the transition texture in advanced tilesets).
- `frames_duration`: Animation frame count for animation styles: 4, 6, 8, 10, 12, or 16.
- `height` (integer, required): Output height in pixels. Each style enforces its own limits; check list_available_styles or get_style_usage.
- `include_downloadable_data`: Include extra structured assets when available (e.g. tileset atlas JSON, animation frame data).
- `input_image`: Base64 PNG used as the main source image for edits, variations, tilesets, animations, or styles that require a starting frame. Raw base64 or a data URL.
- `input_palette`: Base64 image of a color palette; output colors are constrained to it.
- `num_images` (integer): How many images to generate in one batch. Style-specific maximums apply.
- `prompt` (string, required): Describe the SUBJECT only (e.g. 'a knight resting by a campfire'). Never write 'pixel art' — the selected style handles all rendering.
- `prompt_style` (string, required): Style id from list_available_styles (e.g. 'rd_fast__default', 'rd_pro__isometric', or a custom 'user__...' style).
- `rd_api_key`: RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.
- `reference_images`: Extra per-inference guidance images (base64), only for styles where supports_reference_images is true. Not for defining custom styles.
- `remove_bg` (boolean): Remove the background for transparent output.
- `return_non_bg_removed`: Also return the render from before background removal was applied.
- `return_pre_palette`: Also return the render from before palette constraints were applied.
- `return_spritesheet`: For animation styles: return a PNG sprite sheet instead of a GIF.
- `seed`: Seed for reproducible results; reuse the same seed to iterate on one composition.
- `strength`: How strongly to change input_image, 0-1 (default 0.75). Lower values keep more of the original.
- `tile_x` (boolean): Make the result tile seamlessly on the horizontal axis.
- `tile_y` (boolean): Make the result tile seamlessly on the vertical axis.
- `timeout_seconds`: Read-timeout override in seconds for this call; increase for animations or large batches.
- `upload_outputs` (boolean): Host outputs and return URLs in output_urls (recommended for MCP clients) instead of only base64 payloads.
- `upscale_output_factor`: Integer upscale factor for the output image; 1 returns the native pixel size.
- `width` (integer, required): Output width in pixels. Each style enforces its own limits; check list_available_styles or get_style_usage.

### `get_inference_job` (~101 tokens)

Check Async Job

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).

Input parameters:

- `rd_api_key`: RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.
- `task_id` (string, required): Async job id returned by start_inference_job.

### `list_inference_jobs` (~140 tokens)

List Async Jobs

List your most recent async jobs, newest first (GET /v1/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.

Input parameters:

- `limit` (integer): Maximum number of recent jobs to return (1-100, default 20).
- `rd_api_key`: RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.
- `status`: Optional: only return jobs with this status.

### `get_service_status` (~29 tokens)

Service Status

Check RetroDiffusion subsystem health (/v1/status, no auth). Useful before bulk generation runs.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-retrodiffusion-pixel-art/mcp#diagnostics

## Score history

- 2026-08-03: 62
- 2026-08-02: 62
- 2026-08-01: 61
- 2026-07-31: 61
- 2026-07-30: 60
- 2026-07-29: 60
- 2026-07-28: 59
- 2026-07-27: 58
- 2026-07-26: 58

## Links

- Remote endpoint: https://mcp.retrodiffusion.ai/mcp
- Authorisation metadata: https://mcp.retrodiffusion.ai/.well-known/oauth-protected-resource/mcp
- Repository: https://github.com/Retro-Diffusion/retro-diffusion-mcp
- Website: https://retrodiffusion.ai/
- Changelog RSS feed: https://verifymcp.io/servers/ai-retrodiffusion-pixel-art/mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-retrodiffusion-pixel-art/mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/ai-retrodiffusion-pixel-art/mcp