Generate authentic pixel art - sprites, animations, and tilesets - from any MCP client
If you already use Retro Diffusion Pixel Art, the retro diffusion pixel art mcp server is the piece that lets your assistant work with it directly. Generate authentic pixel art - sprites, animations, and tilesets - from any MCP client.
Generate real pixel art — sprites, characters, animations, and tilesets — from any MCP-capable AI assistant.
Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
create_inference — Generate images, animations (GIF/sprite sheet), or tilesets. Returns hosted URLs and a recovery request_id; prefer RD Pro styles for top qualityget_inference_result — Recover or refresh signed output URLs for a successful synchronous generation without generating or charging againstart_inference_job — Start generation as an async job — recommended for animations and batchesget_inference_job — Poll an async job for status and resultslist_inference_jobs — List your recent async jobs — recover a task_id after a lost submission response instead of re-submitting and double-chargingestimate_inference_cost — Free price check for any generation before running itlist_edit_tools — Enabled edit tools with their fields, costs, and limitsrun_edit_tool — Run an edit tool: background remover, palette converter, color reducer, pixel correction, rotation, K-centroid downscale (free–$0.01) · image editestimate_edit_tool_cost — Free cost/duration estimate for any editfix_pixel_art — Free recovery of the native pixel grid from enlarged, softened, AI-rendered, or compressed pixel artlist_available_styles — Live style catalog with per-style size limits and capabilitieslist_available_models — The model families: RD Fast, RD Plus, RD Pro, RD MiniConfiguration is passed through the environment: YOUR_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Retro Diffusion Pixel Art's toolset — create_inference, get_inference_result, start_inference_job and 11 more — is a fair guide to whether it matches your workflow. It is maintained by ai.retrodiffusion; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Retro Diffusion Pixel Art's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| create_inference | Generate images, animations (GIF/sprite sheet), or tilesets. Returns hosted URLs and a recovery request_id; prefer RD Pro styles for top quality |
| get_inference_result | Recover or refresh signed output URLs for a successful synchronous generation without generating or charging again |
| start_inference_job | Start generation as an async job — recommended for animations and batches |
| get_inference_job | Poll an async job for status and results |
| list_inference_jobs | List your recent async jobs — recover a task_id after a lost submission response instead of re-submitting and double-charging |
| estimate_inference_cost | **Free** price check for any generation before running it |
| list_edit_tools | Enabled edit tools with their fields, costs, and limits |
| run_edit_tool | Run an edit tool: background remover, palette converter, color reducer, pixel correction, rotation, K-centroid downscale (free–$0.01) · image edit, inpainting, outpainting, seam tiling (premium) |
| estimate_edit_tool_cost | **Free** cost/duration estimate for any edit |
| fix_pixel_art | **Free** recovery of the native pixel grid from enlarged, softened, AI-rendered, or compressed pixel art |
| list_available_styles | Live style catalog with per-style size limits and capabilities |
| list_available_models | The model families: RD Fast, RD Plus, RD Pro, RD Mini |
| get_style_usage | Usage guidance and constraints for a specific style |
| create_user_style | Create a custom style from a reference image (RD Pro template) |
| Variable | Description | Required |
|---|---|---|
| YOUR_API_KEY | Credential the server authenticates with. | Yes |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.