mcp server
Retro Diffusion Pixel Art
Generate authentic pixel art - sprites, animations, and tilesets - from any MCP client
Description as published by the maintainer. Source
- version 1.1.0
- active
- image generation
active — Most recent push to the repository was 2026-08-02. Dashed tags are derived by ZBS Index from the published description, not stated by the maintainer.
What this server can do
20 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.
authenticate(api_key)- Authenticate this MCP session with a RetroDiffusion public API key. Required: api_key.
create_inference(seed, width, height, prompt, tile_x, tile_y, strength, remove_bg, num_images, rd_api_key, input_image, extra_prompt, prompt_style, input_palette, upload_outputs, frames_duration, timeout_seconds, reference_images, extra_input_image, return_pre_palette, return_spritesheet, return_non_bg_removed, upscale_output_factor, bypass_prompt_expansion, include_downloadable_data)- 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. Required: prompt, prompt_style, width, height.
create_user_style(name, min_width, min_height, rd_api_key, style_icon, description, force_palette, force_bg_removal, llm_instructions, reference_images, reference_caption, apply_prompt_fixer, user_prompt_template, style_reference_images, style_reference_caption, expanded_llm_instructions)- 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`. Required: name.
delete_user_style(style_id, rd_api_key)- Delete a user style using /v1/styles/{style_id}. style_id can be either internal id or prompt_style/public_id. Required: style_id.
estimate_edit_tool_cost(width, height, prompt, tile_x, tile_y, tool_id, expand_top, mask_image, rd_api_key, seam_width, color_count, dither_mode, expand_left, input_image, expand_right, soft_inpaint, expand_bottom, input_palette, dither_strength, timeout_seconds, rotation_degrees, extra_input_image, force_solid_pixels, repair_window_size, transparency_threshold)- Validate an edit-tool request and estimate its cost and duration without running it. Always free. Required: tool_id, input_image.
estimate_inference_cost(width, height, prompt, strength, num_images, rd_api_key, input_image, extra_prompt, prompt_style, input_palette, frames_duration, timeout_seconds, reference_images, extra_input_image, return_pre_palette, return_spritesheet, return_non_bg_removed, upscale_output_factor, bypass_prompt_expansion, include_downloadable_data)- 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. Required: prompt, prompt_style, width, height.
fix_pixel_art(width, engine, height, image_url, rd_api_key, input_image, timeout_seconds)- 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.
get_balance(rd_api_key)- Get credits/balance using the public /v1/inferences/credits endpoint.
get_inference_job(task_id, rd_api_key)- 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). Required: task_id.
get_inference_result(rd_api_key, request_id)- 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. Required: request_id.
get_service_status- Check RetroDiffusion subsystem health (/v1/status, no auth). Useful before bulk generation runs.
get_style_usage(rd_api_key, prompt_style)- 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`. Required: prompt_style.
list_available_models(rd_api_key)- Return unique public model identifiers available in /v1/styles/selector.
list_available_styles(tab, model, rd_api_key)- 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_edit_tools(rd_api_key)- 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.
list_inference_jobs(limit, status, rd_api_key)- 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.
logout- Clear the authenticated RetroDiffusion API key for this MCP session.
run_edit_tool(seed, width, height, prompt, tile_x, tile_y, tool_id, expand_top, mask_image, rd_api_key, seam_width, color_count, dither_mode, expand_left, input_image, expand_right, soft_inpaint, expand_bottom, input_palette, dither_strength, timeout_seconds, rotation_degrees, extra_input_image, force_solid_pixels, repair_window_size, transparency_threshold)- 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. Required: tool_id, input_image.
start_inference_job(seed, width, height, prompt, tile_x, tile_y, strength, remove_bg, num_images, rd_api_key, input_image, extra_prompt, prompt_style, input_palette, upload_outputs, frames_duration, timeout_seconds, reference_images, extra_input_image, return_pre_palette, return_spritesheet, return_non_bg_removed, upscale_output_factor, bypass_prompt_expansion, include_downloadable_data)- 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. Required: prompt, prompt_style, width, height.
update_user_style(name, style_id, min_width, min_height, rd_api_key, style_icon, description, force_palette, force_bg_removal, llm_instructions, reference_images, reference_caption, apply_prompt_fixer, user_prompt_template, style_reference_images, reset_forced_dimensions, style_reference_caption, expanded_llm_instructions)- 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`. Required: style_id.
Last successful function declaration observed on . Source: https://mcp.retrodiffusion.ai/mcp. We list what the server declared; we do not call any of these functions.
Endpoint status observed on . Source: https://mcp.retrodiffusion.ai/mcp.
Signals
These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.
| Signal | Value | What it measures | Window | Observed | Source |
|---|---|---|---|---|---|
| GitHub stars | 1 | Number of GitHub accounts that bookmarked this repository since it was created. It is a bookmark count, not installs, not active users and not quality. | cumulative, all time | GitHub | |
| Last commit | 2026-08-02 | Date of the most recent push to any branch. This is the strongest cheap indicator of whether the project is still maintained. | point in time | GitHub | |
| Open issues | 1 | Open issues plus open pull requests, as GitHub counts them together. A high number can mean an active project or an abandoned one. | as of fetch | GitHub | |
| Latest published version | 1.1.0 | Latest version string the maintainer published to the registry. | as of fetch | Model Context Protocol | |
| Registry record last updated | 2026-07-10 | When the registry record was last updated by its maintainer. | point in time | Model Context Protocol | |
| License | MIT | Licence GitHub detected in the repository. Detection can be wrong; the LICENSE file is authoritative. | as of fetch | GitHub | |
| First listed in the MCP Registry | 2026-07-10 | Date this server was first published to the official MCP Registry. Not a usage or quality measure. | point in time | Model Context Protocol | |
| repository status | active | The repository exists on GitHub and is not archived. This says nothing about how recently it was worked on. | as of fetch | GitHub | |
| mcp tools declared | 20 tools | Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. | as of probe | mcp.retrodiffusion.ai | |
| mcp endpoint status | ok | The server listed 20 functions when asked. | as of probe | mcp.retrodiffusion.ai |
Where to get it
This record as data
Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.
GET /api/v1/entries/mcp_server.json