Retro Diffusion Pixel Art MCP Server

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.

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).

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.

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.

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`.

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

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`.

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

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.

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.

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.

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

Authenticate this MCP session with a RetroDiffusion public API key.

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

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.

Clear the authenticated RetroDiffusion API key for this MCP session.

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

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.

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`.