Retro Diffusion Pixel Art is an MCP server with 20 tools an agent can call, among them authenticate, create_inference, create_user_style. It answers at https://mcp.retrodiffusion.ai/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 4 September 2026; the last check, on 17 October 2026, succeeded.
Generate authentic pixel art - sprites, animations, and tilesets - from any MCP client
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
authenticate | Authenticate this MCP session with a RetroDiffusion public API key. Inputs: api_key |
create_inference | 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 Inputs: prompt, prompt_style, width, height, num_images, input_image |
create_user_style | 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 `refere Inputs: name, description, style_icon, reference_images, style_reference_images, reference_caption |
delete_user_style | Delete a user style using /v2/styles/{style_id}. style_id can be either internal id or prompt_style/public_id. Inputs: style_id, rd_api_key |
estimate_edit_tool_cost | Validate an edit-tool request and estimate its cost and duration without running it. Always free. Inputs: tool_id, input_image, prompt, mask_image, extra_input_image, input_palette |
estimate_inference_cost | 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 Inputs: prompt, prompt_style, width, height, num_images, input_image |
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 repa Inputs: input_image, image_url, engine, width, height, timeout_seconds |
get_balance | Get credits/balance using the public /v2/inferences/credits endpoint. Inputs: rd_api_key |
get_inference_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). Inputs: task_id, rd_api_key |
get_inference_result | 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 Inputs: request_id, rd_api_key |
get_service_status | Check RetroDiffusion subsystem health (/v2/status, no auth). Useful before bulk generation runs. |
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 `sty Inputs: prompt_style, rd_api_key |
list_available_models | Return unique public model identifiers available in /v2/styles/selector. Inputs: rd_api_key |
list_available_styles | 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. Inputs: model, tab, rd_api_key |
list_edit_tools | 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, Inputs: rd_api_key |
list_inference_jobs | 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 Inputs: limit, status, rd_api_key |
logout | Clear the authenticated RetroDiffusion API key for this MCP session. |
run_edit_tool | 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_edi Inputs: tool_id, input_image, prompt, mask_image, extra_input_image, input_palette |
start_inference_job | 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 outliv Inputs: prompt, prompt_style, width, height, num_images, input_image |
update_user_style | 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_ima Inputs: style_id, name, description, style_icon, reference_images, style_reference_images |
Every block below points at https://mcp.retrodiffusion.ai/mcp. Pick your client and copy.
claude mcp add --transport http retro-diffusion-pixel-art https://mcp.retrodiffusion.ai/mcp
{
"mcpServers": {
"retro-diffusion-pixel-art": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.retrodiffusion.ai/mcp"]
}
}
}{
"mcpServers": {
"retro-diffusion-pixel-art": {
"url": "https://mcp.retrodiffusion.ai/mcp"
}
}
}{
"servers": {
"retro-diffusion-pixel-art": {
"type": "http",
"url": "https://mcp.retrodiffusion.ai/mcp"
}
}
}{
"context_servers": {
"retro-diffusion-pixel-art": {
"url": "https://mcp.retrodiffusion.ai/mcp"
}
}
}{
"mcpServers": {
"retro-diffusion-pixel-art": {
"serverUrl": "https://mcp.retrodiffusion.ai/mcp"
}
}
}{
"mcpServers": {
"retro-diffusion-pixel-art": {
"url": "https://mcp.retrodiffusion.ai/mcp"
}
}
}name: Retro Diffusion Pixel Art
version: 0.0.1
schema: v1
mcpServers:
- name: Retro Diffusion Pixel Art
type: streamable-http
url: https://mcp.retrodiffusion.ai/mcp{
"mcpServers": {
"retro-diffusion-pixel-art": {
"httpUrl": "https://mcp.retrodiffusion.ai/mcp"
}
}
}{
"mcpServers": {
"retro-diffusion-pixel-art": {
"type": "http",
"url": "https://mcp.retrodiffusion.ai/mcp"
}
}
}{
"mcpServers": {
"retro-diffusion-pixel-art": {
"url": "https://mcp.retrodiffusion.ai/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fmcp.retrodiffusion.ai%2Fmcp&type=streamable_http&id=retro-diffusion-pixel-art&name=Retro%20Diffusion%20Pixel%20Art
It answered our last check on 17 October 2026 in 307 ms. Over 10 checks since 4 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by retrodiffusion.ai and served from mcp.retrodiffusion.ai, the vendor's own domain: https://mcp.retrodiffusion.ai/mcp.
20, as returned by the server's own tools/list on 8 September 2026: authenticate, create_inference, create_user_style, delete_user_style, estimate_edit_tool_cost, estimate_inference_cost, fix_pixel_art, get_balance, and 12 more.
It answered our last check on 17 October 2026 in 307 ms. Over 10 checks since 4 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp.retrodiffusion.ai/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: ai.retrodiffusion. Endpoint host: mcp.retrodiffusion.ai. ARD identifier: urn:air:ai.retrodiffusion:mcp:pixel-art.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.