# Retro Diffusion Pixel Art MCP server

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

## Links
- Registry page: https://www.getdrio.com/mcp/ai-retrodiffusion-pixel-art
- Repository: https://github.com/Retro-Diffusion/retro-diffusion-mcp
- Website: https://retrodiffusion.ai

## Install
- Endpoint: https://mcp.retrodiffusion.ai/mcp
- Auth: Auth required by registry metadata

## Setup notes
- Remote header: Authorization (required; secret)
- The upstream registry signals required auth or secrets.
- Remote endpoint: https://mcp.retrodiffusion.ai/mcp
- Header: Authorization

## Tools
- authenticate (Authenticate) - Authenticate this MCP session with a RetroDiffusion public API key. Endpoint: https://mcp.retrodiffusion.ai/mcp
- logout (Log Out) - Clear the authenticated RetroDiffusion API key for this MCP session. Endpoint: https://mcp.retrodiffusion.ai/mcp
- create_user_style (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`. Endpoint: https://mcp.retrodiffusion.ai/mcp
- update_user_style (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`. Endpoint: https://mcp.retrodiffusion.ai/mcp
- delete_user_style (Delete Custom Style) - Delete a user style using /v1/styles/{style_id}.
style_id can be either internal id or prompt_style/public_id. Endpoint: https://mcp.retrodiffusion.ai/mcp
- list_available_styles (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. Endpoint: https://mcp.retrodiffusion.ai/mcp
- list_available_models (List Models) - Return unique public model identifiers available in /v1/styles/selector. Endpoint: https://mcp.retrodiffusion.ai/mcp
- get_style_usage (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`. Endpoint: https://mcp.retrodiffusion.ai/mcp
- get_balance (Get Balance) - Get credits/balance using the public /v1/inferences/credits endpoint. Endpoint: https://mcp.retrodiffusion.ai/mcp
- estimate_inference_cost (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. Endpoint: https://mcp.retrodiffusion.ai/mcp
- create_inference (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. Endpoint: https://mcp.retrodiffusion.ai/mcp
- list_edit_tools (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. Endpoint: https://mcp.retrodiffusion.ai/mcp
- fix_pixel_art (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. Endpoint: https://mcp.retrodiffusion.ai/mcp
- run_edit_tool (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. Endpoint: https://mcp.retrodiffusion.ai/mcp
- estimate_edit_tool_cost (Estimate Edit Cost (Free)) - Validate an edit-tool request and estimate its cost and duration without running it. Always free. Endpoint: https://mcp.retrodiffusion.ai/mcp
- get_inference_result (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. Endpoint: https://mcp.retrodiffusion.ai/mcp
- start_inference_job (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. Endpoint: https://mcp.retrodiffusion.ai/mcp
- get_inference_job (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). Endpoint: https://mcp.retrodiffusion.ai/mcp
- list_inference_jobs (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. Endpoint: https://mcp.retrodiffusion.ai/mcp
- get_service_status (Service Status) - Check RetroDiffusion subsystem health (/v1/status, no auth). Useful before bulk generation runs. Endpoint: https://mcp.retrodiffusion.ai/mcp

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: ai.retrodiffusion
- Version: 1.1.0
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Jul 10, 2026
- Source: https://registry.modelcontextprotocol.io