Ludo AI Game Assets
MCP server by Ludo.ai
Generate game sprites, animations, 3D models, video, music, sound effects and voices with Ludo.ai
Connect to Ludo AI Game Assets
Ludo AI Game Assets needs an API key. Connect with its own URL and your key:
Send your key in the Authorization header. mcp.tc never sees or stores keys. Where to get a key
Share this server
Opens this page, with the URL and setup steps.
mcp.tc/i/ludo-ai-game-assetsAbout
Connects to Ludo.ai to generate game assets from an assistant. It covers images and sprites, animated spritesheets, directional sprites from 3D models, 3D model creation with rigging and animation, short videos, sound effects, ambiance, music and voices. It also includes tools to search Ludo's documentation and list past generations.
Runs as a hosted Streamable HTTP endpoint at https://mcp.ludo.ai/mcp. Requests need an Authorization header with a Ludo API key (ApiKey YOUR_API_KEY). API access comes with the Pro and Studio plans. Generation tools return a job ID to poll, and returned asset URLs expire after 7 days, so download results promptly.
What you can do
- Generate game art images and restyle from a reference image
- Animate sprites into spritesheets from prompts or keyframes
- Create, rig and animate 3D models
- Render directional sprites from 3D models
- Generate videos from images and edit or upscale them
- Create sound effects, ambiance, music and voices
- Remove backgrounds, upscale images, convert to pixel art
- Search Ludo docs and list past generations
Tools 54
validateApiKeyEndpointRead-onlyCheck whether an API key is valid.
createImageWritesGenerate game-art images from a text prompt.
generateWithStyleWritesGenerate new images matching a reference image's style.
editImageWritesModify an existing image using text instructions.
animateSpriteWritesTurn a static sprite into a spritesheet from a motion prompt.
animateSpriteKeyframesWritesAnimate a sprite through up to three keyframes.
generatePoseWritesRe-pose an existing sprite while keeping the character.
rotateSpriteWritesRe-render a sprite from a different camera viewpoint.
transferMotionWritesApply motion from a video or preset onto a sprite.
getDocsRead-onlyBrowse or read Ludo documentation.
searchDocsRead-onlySearch Ludo documentation with a plain-language question.
listAnimationPresetsRead-onlyList animation presets, perspectives and directions.
Show 42 more tools
editSpritesheetWritesRe-prompt, outpaint or repair a generated spritesheet.
rotateSpritesheetWritesRe-render a sprite animation from a new view.
adjustSpritesheetWritesRe-export a spritesheet with different sheet settings.
createSpriteAudioWritesGenerate a sound effect for a spritesheet animation.
listDirectionalSpriteStylesRead-onlyList styles, perspectives and directions for directional sprites.
previewDirectionalSpritesWritesPreview a few frames of a 3D model in a style.
createDirectionalSpritesWritesRender a 3D model into one spritesheet per direction.
createDirectionalStillsWritesRender a 3D model into one still image per direction.
fitDirectionalAccessoryWritesFit an accessory to a 3D model
attachDirectionalAccessoriesWritesAttach accessories to a 3D model
createVideoWritesGenerate a short video from a source image and motion prompt.
createVideoFromReferencesWritesGenerate a video from 1-5 reference images and a prompt.
editVideoWritesEdit a generated video with a text prompt.
upscaleVideoWritesUpscale a generated video to twice its resolution.
removeBackgroundWritesIsolate the subject on a transparent background.
upscaleImageWritesUpscale an image up to 4x.
createNormalMapWritesMake a normal map of an image
convertToPixelArtWritesConvert an image to pixel art, free and synchronous.
createTileWritesCreate seamless map tile
createTilesetWritesCreate 16-tile tileset
editTilesetWritesEdit tileset
create3DModelWritesConvert a source image into a textured GLB 3D model.
create3DModelImageWritesMake a character image ready for 3D model conversion.
rigModelWritesGenerate a skeleton and skin weights for a GLB.
animate3DModelWritesGenerate text-driven animations for a rigged model.
animate3DModelPresetWritesApply an animation preset to a rigged model.
createAnimationWritesCreate reusable animation from a prompt
listMyAnimationsRead-onlyList your generated animations
createSoundEffectWritesProduce a short sound effect from a text description.
createAmbianceWritesProduce a looping ambiance soundscape from text.
createMusicWritesProduce music from a description, with optional lyrics.
createAudioTransformWritesRemix an existing audio sample guided by a prompt.
createVoiceWritesDesign a new voice from a character description or image.
createSpeechWritesText to speech by cloning a voice from an audio sample.
createSpeechPresetWritesText to speech with a built-in preset voice.
listGenerationsRead-onlyList past generations with filters and pagination.
listApiJobsRead-onlyList jobs
getApiJobRead-onlyGet job status and results
cancelApiJobCan deleteCancel job
getPricingRead-onlyGet Ludo plans and pricing
getAccountRead-onlyGet credits and plan
submitApiFeedbackWritesSend feedback to Ludo
Read from the live server on 18 Nov 2026. Read-only, Writes and Can delete are hints the server declares; your client decides whether to ask before running a tool.
Example prompts
Create a pixel art knight sprite and animate a walk cycle
Turn this character image into a rigged 3D model
Generate a looping windy forest ambiance for my level
Remove the background from this image and upscale it 2x
Set up
Every client connects to mcp.ludo.ai. Pick yours; the page remembers your choice.
Claude Code
- Run this in a terminal, in your project folder:
claude mcp add --transport http ludo-ai-game-assets https://mcp.ludo.ai/mcp --header "Authorization: Bearer <YOUR_API_KEY>"- Replace the placeholder with your key before you run it, then check it with
/mcpinside Claude Code.
Add --scope user to make it available in every project, not just this one.
Claude Desktop
- Use the
mcp-remotebridge, which keeps the key on this computer (a connector added on claude.ai with the key under Request headers also shows up here). Open Settings → Developer → Edit Config and add:
{
"mcpServers": {
"ludo-ai-game-assets": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://mcp.ludo.ai/mcp",
"--header",
"Authorization: Bearer <YOUR_API_KEY>"
]
}
}
}- Replace the placeholder with your key and restart Claude Desktop.
The bridge needs Node.js on your computer.
claude.ai
- Open the connector form on claude.ai. This button fills in the name and URL for you:
Add to claude.ai (opens in a new tab)
- Check that the URL reads
https://mcp.ludo.ai/mcp. Under Request headers, addAuthorization: Bearer <YOUR_API_KEY>with your key from Ludo.ai, then click Add. - Turn it on in a chat from the tools menu.
Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under Organization settings → Connectors.
Cursor
Add to Cursor (opens in a new tab)
Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):
{
"mcpServers": {
"ludo-ai-game-assets": {
"url": "https://mcp.ludo.ai/mcp",
"headers": {
"Authorization": "Bearer <YOUR_API_KEY>"
}
}
}
}VS Code
Add it to .vscode/mcp.json. VS Code asks for the key the first time and stores it securely:
{
"servers": {
"ludo-ai-game-assets": {
"type": "http",
"url": "https://mcp.ludo.ai/mcp",
"headers": {
"Authorization": "Bearer ${input:api-key}"
}
}
},
"inputs": [
{
"type": "promptString",
"id": "api-key",
"description": "API key",
"password": true
}
]
}Devin Desktop
- Add it to
~/.config/devin/mcp_config.json(macOS and Linux) or%APPDATA%\devin\mcp_config.json(Windows):
{
"mcpServers": {
"ludo-ai-game-assets": {
"serverUrl": "https://mcp.ludo.ai/mcp",
"headers": {
"Authorization": "Bearer <YOUR_API_KEY>"
}
}
}
}- Refresh the MCP server list in Cascade.
Devin Desktop is the new name for Windsurf. It reads serverUrl (or url) for remote servers.
Codex
codex mcp add ludo-ai-game-assets --url https://mcp.ludo.ai/mcp --bearer-token-env-var LUDO_AI_GAME_ASSETS_API_KEYOr edit ~/.codex/config.toml directly:
[mcp_servers.ludo-ai-game-assets]
url = "https://mcp.ludo.ai/mcp"
bearer_token_env_var = "LUDO_AI_GAME_ASSETS_API_KEY"Set LUDO_AI_GAME_ASSETS_API_KEY to your key in the shell that runs Codex.
Gemini CLI
gemini mcp add --transport http --header "Authorization: Bearer <YOUR_API_KEY>" ludo-ai-game-assets https://mcp.ludo.ai/mcpThis adds it to the current project. Add -s user to use it everywhere.
Any client
Most clients accept this shape. Some name the URL field differently: serverUrl in Devin Desktop, httpUrl in Gemini CLI’s settings file.
{
"mcpServers": {
"ludo-ai-game-assets": {
"type": "http",
"url": "https://mcp.ludo.ai/mcp",
"headers": {
"Authorization": "Bearer <YOUR_API_KEY>"
}
}
}
}Zed puts servers under context_servers in its settings. Cline needs "type": "streamableHttp", or it assumes SSE.
Client only starts local servers? Bridge it with npx -y mcp-remote https://mcp.ludo.ai/mcp.
Embed
Show Ludo AI Game Assets in a README or on your site. Each embed links to this page, uses the server’s own URL, and sets no cookies. How embeds work
The card, the iframe and the JSON are in English. Add ?lang=it, fr, de or es to their address for another language.
README badge
[](https://mcp.tc/i/ludo-ai-game-assets)<a href="https://mcp.tc/i/ludo-ai-game-assets"><img src="https://mcp.tc/i/ludo-ai-game-assets/badge.svg" alt="Ludo AI Game Assets on mcp.tc" height="20"></a>It follows the reader’s light or dark mode. Add ?theme=light or ?theme=dark to fix it, or ?style=compact to show the mark without the word.
Website card
<script src="https://mcp.tc/w/ludo-ai-game-assets.js" async></script>The card appears where the tag is. Add data-theme="dark" or data-size="compact" to the tag to change it. The file holds everything it needs, so it makes no other requests and sets no cookies.
iframe
<iframe src="https://mcp.tc/embed/ludo-ai-game-assets" title="Ludo AI Game Assets on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>Use it on pages that don’t allow scripts. Add ?theme=light or ?theme=dark to the address to fix the colors.
JSON
The listing as data for your own pages and tools: name, tagline, the server’s own URL, tools and the “Add to” links. Any site can read it (CORS is open).
https://mcp.tc/i/ludo-ai-game-assets.jsonAI prompt
Paste this into an AI coding assistant, such as Claude Code or Cursor, and it adds the Ludo AI Game Assets card to your site.
Add the mcp.tc card for Ludo AI Game Assets, an MCP server, to my website. It is one static script: no build step, no package to install, no cookies.
Put this tag where the card should appear. The card renders right before it:
```html
<script src="https://mcp.tc/w/ludo-ai-game-assets.js" async></script>
```
To show the card somewhere else, put this placeholder there and load the same script once, for example before `</body>`. Keep the link inside: visitors without JavaScript see it.
```html
<div data-mcptc="ludo-ai-game-assets"><a href="https://mcp.tc/i/ludo-ai-game-assets">Ludo AI Game Assets on mcp.tc</a></div>
```
Options:
- `data-theme="light"` or `"dark"` on the tag or the placeholder fixes the colors. Without it, the card follows the visitor’s light or dark mode.
- `data-size="compact"` gives a smaller card without the tagline.
- The CSS variable `--mcptc-max-width` on the placeholder or a parent sets the width (default `520px`).
- `?lang=` on the script URL sets the card’s language: `en`, `it`, `fr`, `de` or `es`.
If the site has a Content Security Policy, allow `script-src https://mcp.tc` and `img-src data:` (the icon is inline).
For a README or other Markdown docs, use the badge instead:
```markdown
[](https://mcp.tc/i/ludo-ai-game-assets)
```
Reference: https://mcp.tc/embedChange history
We read this server’s tool list every 3 hours and record what changes. Last read 18 Nov 2026, 02:44 UTC.
-
3 tools added and 5 tools changed.
Details, 17 Nov 2026, 14:53 UTC
Added 3
createTileWritesMake a seamless base tile for a 2D map from a text description: the first step of a tileset. Choose the map's grid (square for top-down, diamond for 2:1 isometric, diamond-true for true isometric) and what to make with image_type: texture (the default) is a ground that repeats with no seams, one per terrain (grass, sand, cobblestones, water); sprite-tiling-horizontal and sprite-tiling-vertical are a strip of a line that repeats along it (a road, a river, a fence, a wall) on a transparent background, and scatter-pattern the separate elements a line is made of (rocks, bushes, flowers). The look comes from art_style or from a reference_image (URL or base64), which replaces the art style. The job result is an array of tiles, each with its url, the image type the tile came back with and the grid it was made for; request n (1-4) for more candidates. Pass a tile's url as tile_a or tile_b of createTileset on the same grid to build a 16-tile set from it. For a single seamless texture that is n…
createTilesetWritesBuild a 16-tile tileset from seamless base tiles: every arrangement a map needs, so the edges and corners fall into place when a map is painted with it. kind terrain (the default) blends terrain A (tile_a, required) into terrain B (tile_b; leave it out and the tiles are cut out there, transparent, for floors over a void or islands), with the boundary described in transition (e.g. white sea foam, a low stone curb): its 16 tiles cover every way the two terrains meet at a tile's four corners. kind lines lays a line (tile_b, required: a strip or scatter made by createTile, or a ground tile of the line's material) over a ground (tile_a, optional: without it the set is a transparent overlay), in every dead end, straight, turn, T and crossing: its 16 tiles cover every way the line leaves a tile by its four sides. Both tiles must be for the set's grid. Pass tiles as the url createTile returned (the tile is then read with its type, which gives the best result) or as any image by URL or base64,…
editTilesetWritesChange a whole tileset with one sentence: its look (cover the ground in snow, at sunset, another art style) or its boundary (replace the curb with a hedge). The set is one you made with createTileset or in the Ludo web app, given by its atlas_url; any other URL is rejected with HTTP 404 before credits are held. The result is a new tileset of the same grid and kind whose 16 tiles fit together the same way, so it drops into a map painted with the original; the original is kept. save_normals adds a normal map of the new atlas. The job result has the same shape as createTileset's. Credits are held when the job is accepted and refunded if it fails or is cancelled. Pass an optional request_id to tag the result so you can retrieve it later via listGenerations (type tileset). Async generation job: returns `{id, status}` - poll `getApiJob` (job and credit contract: see the server instructions). Credits: This endpoint consumes 2 credits per call.
Changed 5
animateSpriteinput schemaanimateSpriteKeyframesinput schemacreate3DModeldescriptionBeforeConvert a source image into a textured 3D model (image-to-3D). The job result is a downloadable GLB model_url plus an array of snapshot image URLs rendered from different angles (handy for previews). model picks the generator: prop (default) is low-cost and suits everyday props and environment pieces; hero is far more detailed and accurate, for close-up assets, but slower and more expensive. image is the front view; with prop, pass an optional back_image (the same subject seen from behind) so the back of the model follows it instead of being invented - hero takes the front image only and rejects a back_image with HTTP 400. The image is converted as it is: to make a character image for it first, from a prompt or by redrawing your own image as a 3D render, use create3DModelImage. Accepts optional mesh controls: target_num_faces (max
triangle count, 1000-200000, default 50000), texture_size (1024 or 2048, default 2048), and texture_type ("pbr", "simple", or "none", default "pbr"). Pass r…AfterConvert a source image into a textured 3D model (image-to-3D). The job result is a downloadable GLB model_url plus an array of snapshot image URLs rendered from different angles (handy for previews). model picks the generator: prop (default) is low-cost and suits everyday props and environment pieces; hero is far more detailed and accurate, for close-up assets, but slower and more expensive. image is the front view; with prop, pass an optional back_image (the same subject seen from behind) so the back of the model follows it instead of being invented - hero takes the front image only and rejects a back_image with HTTP 400. The image is converted as it is: to make a character image for it first, from a prompt or by redrawing your own image as a 3D render, use create3DModelImage. Flat 2D art (outlines and flat colours, no shading) can come back as a flat card instead of a solid model: redraw it with create3DModelImage first. Accepts optional mesh controls: target_num_faces (max triangle…
editSpritesheetinput schemalistGenerationsinput schema
-
1 tool changed.
Details, 17 Nov 2026, 11:51 UTC
Changed 1
createVideoinput schema
-
7 tools changed.
Details, 16 Nov 2026, 14:52 UTC
Changed 7
animateSpritedescription and input schemaThe text shown here is the same before and after: the change is past the first 1,000 characters or in characters that don’t show.
animateSpriteKeyframesdescription and input schemaBeforeAnimate a sprite through up to three fixed keyframes - initial_image, middle_image and final_image (each a URL or base64) - producing a spritesheet that interpolates through the provided frames in order. initial_image is required: the animation starts from it, and middle_image and final_image add keyframes after it (either may be omitted). The motion_prompt is optional here - when omitted, the motion is derived purely from the keyframes. Runs on hydra (default; also returns `audio_url`), hydra-plus (hydra with finer detail, also returns `audio_url`),
forge,orforge-pixelfor pixel-art sprites - the models that support a middle keyframe; any other model returns HTTP 400. For just a start and end frame, animateSprite with `final_image` does the same job. The job result is the same sprite result as animateSprite (`spritesheet_url`, `video_url`, grid fields, optional GIF and frame URLs, `audio_url` onhydraandhydra-plus).Credits are held forthe duration you requested when the job is…AfterAnimate a sprite through up to three fixed keyframes - initial_image, middle_image and final_image (each a URL or base64) - producing a spritesheet that interpolates through the provided frames in order. initial_image is required: the animation starts from it, and middle_image and final_image add keyframes after it (either may be omitted). The motion_prompt is optional here - when omitted, the motion is derived purely from the keyframes. Runs on hydra (default; also returns `audio_url`), hydra-plus (hydra with finer detail, also returns `audio_url`), ignis, or ignis-pixel for pixel-art sprites (forge and forge-pixel are legacy) - the models that support a middle keyframe; any other model returns HTTP 400. For just a start and end frame, animateSprite with `final_image` does the same job. The job result is the same sprite result as animateSprite (`spritesheet_url`, `video_url`, grid fields, optional GIF and frame URLs, `audio_url` on hydra, hydra-plus and ignis). Credits are held for t…
- Description of
requestBodyBeforePayload for generating an animated spritesheet that interpolates through up to three fixed keyframes (initial / middle / final). Runs on hydra (default), hydra-plus,
forgeorforge-pixel -themodels…AfterPayload for generating an animated spritesheet that interpolates through up to three fixed keyframes (initial / middle / final). Runs on hydra (default), hydra-plus, ignis or ignis-pixel (and the leg…
- Description of
createSpriteAudiodescriptionBeforeGenerate a sound effect for a previously generated spritesheet animation. Pass, as `spritesheet_video_url`, the `video_url` you received from `animateSprite`, `animateSpriteKeyframes`, `transferMotion`, or `editSpritesheet` - it must belong to a spritesheet you generated within the last 7 days; arbitrary external videos are not accepted. Spritesheets generated with the hydra
modelalready come with `audio_url`, so only call this forforge / forge-pixel outputor to replacehydra'ssound. Optionally add a `prompt` describing the sound you want. The job result is only the URL of the generated audio file, an MP3 or WAV (the URL's extension, .mp3 or .wav, says which); no video is returned. The audio is also attached to the spritesheet, so it appears as `audio_url` in listGenerations (type spritesheet), where the spritesheet keeps the `request_id` it was generated with. Pass an optional `request_id` to make this call idempotent and to find its job again; it must not beone you already used…AfterGenerate a sound effect for a previously generated spritesheet animation. Pass, as `spritesheet_video_url`, the `video_url` you received from `animateSprite`, `animateSpriteKeyframes`, `transferMotion`, or `editSpritesheet` - it must belong to a spritesheet you generated within the last 7 days; arbitrary external videos are not accepted. Spritesheets generated with the hydra or ignis models already come with `audio_url`, so only call this for a spritesheet that has none or to replace the generated sound. Optionally add a `prompt` describing the sound you want. The job result is only the URL of the generated audio file, an MP3 or WAV (the URL's extension, .mp3 or .wav, says which); no video is returned. The audio is also attached to the spritesheet, so it appears as `audio_url` in listGenerations (type spritesheet), where the spritesheet keeps the `request_id` it was generated with. Pass an optional `request_id` to make this call idempotent and to find its job again; it must not be one…
createVideodescription and input schemaThe text shown here is the same before and after: the change is past the first 1,000 characters or in characters that don’t show.
editSpritesheetdescription and input schemaThe text shown here is the same before and after: the change is past the first 1,000 characters or in characters that don’t show.
generateWithStyleinput schematransferMotiondescription and input schemaBeforeTransfer motion from a reference video, a named animation preset or one of the account's generated animations (an `animation_id` from createAnimation or listMyAnimations) onto a static sprite image, producing an animated spritesheet that mimics the reference movement. Provide the sprite as image (URL or base64) plus either a video
URLor a preset_id together with perspective and direction (all three from listAnimationPresets; ifbothvideo andpreset_id are sentthe videowins).The job result is the same sprite result as animateSprite: `spritesheet_url`, `video_url`, grid fields, optional GIF / frame / with-background URLs, and `audio_url` when the model is hydra. `duration` defaults to 1.5s where the chosen model offers it, otherwise to that model's shortest (hydra, the default, starts at 3s) - and a longer reference clip or preset is compressed to fit, so pass the preset's own `duration` (returned bylistAnimationPresets) to keep its timing. It returns HTTP 400 if neither a video n…AfterTransfer motion from a reference video, a named animation preset or one of the account's generated animations (an `animation_id` from createAnimation or listMyAnimations) onto a static sprite image, producing an animated spritesheet that mimics the reference movement. Provide the sprite as image (URL or base64) plus either a video (URL or base64) or a preset_id together with perspective and direction (all three from listAnimationPresets; if a video is sent with a preset_id or animation_id, the preset or animation is used and the video is ignored). The job result is the same sprite result as animateSprite: `spritesheet_url`, `video_url`, grid fields, optional GIF / frame / with-background URLs, and `audio_url` when the model is hydra. `duration` defaults to 1.5s where the chosen model offers it, otherwise to that model's shortest (hydra, the default, starts at 3s) - and a longer reference clip or preset is compressed to fit, so pass the preset's own `duration` (returned by listAnimatio…
-
3 tools changed.
Details, 11 Nov 2026, 20:58 UTC
Changed 3
createDirectionalSpritesinput schemacreateDirectionalStillsinput schemapreviewDirectionalSpritesinput schema
-
2 tools added and 5 tools changed. Server instructions changed.
New server instructions
Details, 11 Nov 2026, 14:53 UTC
Added 2
createAnimationWritesGenerate a reusable animation from a text prompt (text-to-motion): the skeletal motion of a humanoid character, such as "overhead sword slash" or "zombie walk", made for no model in particular. It is saved to the account and can then be played by any rigged humanoid 3D model or transferred onto any sprite. No model or sprite is animated by this call; to animate one rigged model straight from a prompt, use animate3DModel. The job result is an `animations` array, one animation per num_variants (each with its own seed), each with an `id`, a `name`, the `caption` the motion model was given, its `duration`, whether it loops, and a `preview_url`: an mp4 of the move on a mannequin, seen from the low camera facing SW. There is no GLB yet: use an animation's `id` as `animation_id` wherever an animation preset goes - animate3DModelPreset (retarget it onto a rigged GLB, which gives the GLB), createDirectionalSprites and previewDirectionalSprites (render it on a 3D model from up to 8 directions)…
listMyAnimationsRead-onlyList the account's own animations: the ones generated with createAnimation or in the web app's My Animations, newest first. (Ludo's ready-made ones are listAnimationPresets.) Synchronous GET with no request body: it returns an `animations` array, each with the `id` to pass as `animation_id`, its `name`, the `prompt` it was generated from, its `duration`, whether it loops, and a `preview_url` (an mp4 of the move on a mannequin). Animations do not expire, so call this before generating a move again: one made earlier, for another character or in the web app, can be reused as it is. Pass an animation's `id` as `animation_id` to animate3DModelPreset, createDirectionalSprites, previewDirectionalSprites or transferMotion. 50 animations per call by default; for older ones pass `before` with the `created_at` of the last animation received. This is a free endpoint and does not charge credits.
Changed 5
animate3DModelPresetdescription, title, input schema and hintsBeforeApply a curated animation
presetto an already-rigged 3D model (retargeting). Pass the rigged GLB in `model` (URL or base64; the 3D asset file, not an AI model name) and a `preset_id` from the animation presets list (from listAnimationPresets; any preset idworks).Any rig type can take apreset,though retargeting does not succeed on every model: when it does not, the job fails. The job result is one retargeted animation - a standalone animation-only GLB in `glb_url` plus an mp4 `preview_url` - in the same `animations` envelope as the animate endpoint.crop_loop trims the clipto itsseamlessly-looping span (omit to follow the preset's own loop flag);in_place removes net travel so the character moves on the spot,as game-engine locomotion expects (omit to keep the preset's own travel). Credits are held when the job is accepted and refunded if it fails or is cancelled. Async generation job: returns `{id, status}` - poll `getApiJob` (job and credit contract: see the server instruction…AfterApply a curated animation preset, or one of the account's generated animations, to an already-rigged 3D model (retargeting). Pass the rigged GLB in `model` (URL or base64; the 3D asset file, not an AI model name) and exactly one of a `preset_id` from the animation presets list (from listAnimationPresets; any preset id works) and an `animation_id` (the id of an animation from createAnimation or listMyAnimations). Set `mirror` to play the move on the other side, left and right swapped (a left-handed slash from a right-handed one). Any rig type can take a preset or an animation, though retargeting does not succeed on every model: when it does not, the job fails. The job result is one retargeted animation - a standalone animation-only GLB in `glb_url` plus an mp4 `preview_url` - in the same `animations` envelope as the animate endpoint. An animation that loops is trimmed to its seamless loop; a one-shot keeps its full arc. in_place removes net travel so the character moves on the spot, as…
title
BeforeAnimate 3D model with a preset
AfterAnimate 3D model with a preset or your animation
- Description of
requestBodyBeforePayload for animating a rigged 3D model with a preset animation
AfterPayload for animating a rigged 3D model with a preset animation or a generated animation
- Description of
createDirectionalSpritesinput schemalistAnimationPresetsdescriptionBeforeList the available animation presets along with their perspectives and the eight supported compass directions (N, NE, E, SE, S, SW, W, NW). Synchronous GET with no request body: it returns an animations array (each with id, name, category, description, duration, and preview_url), a deduplicated perspectives array, and the directions list. This is a free discovery endpoint and does not charge credits. Use it to obtain the preset_id, perspective, and direction values that transferMotion needs, and to find motion preset names you can reference when animating; pair it with transferMotion (to apply a preset onto a sprite), animateSprite (text-prompt animation), or animate3DModelPreset (apply any preset by id to a rigged 3D model).
AfterList the available animation presets along with their perspectives and the eight supported compass directions (N, NE, E, SE, S, SW, W, NW). Synchronous GET with no request body: it returns an animations array (each with id, name, category, description, duration, and preview_url), a deduplicated perspectives array, and the directions list. This is a free discovery endpoint and does not charge credits. Use it to obtain the preset_id, perspective, and direction values that transferMotion needs, and to find motion preset names you can reference when animating; pair it with transferMotion (to apply a preset onto a sprite), animateSprite (text-prompt animation), or animate3DModelPreset (apply any preset by id to a rigged 3D model). When no preset covers the move, createAnimation generates one from a text prompt, used by `animation_id` wherever a preset_id goes.
previewDirectionalSpritesinput schematransferMotiondescription and input schemaBeforeTransfer motion from a reference
video ora named animation preset onto a static sprite image, producing an animated spritesheet that mimics the reference movement. Provide the sprite as image (URL or base64) plus either a video URL or a preset_id together with perspective and direction (all three from listAnimationPresets; if both video and preset_id are sent the video wins). The job result is the same sprite result as animateSprite: `spritesheet_url`, `video_url`, grid fields, optional GIF / frame / with-background URLs, and `audio_url` when the model is hydra. `duration` defaults to 1.5s where the chosen model offers it, otherwise to that model's shortest (hydra, the default, starts at 3s) - and a longer reference clip or preset is compressed to fit, so pass the preset's own `duration` (returned by listAnimationPresets) to keep its timing. It returns HTTP 400 if neither a videonor a complete preset_id/perspective/direction triple is supplied, if the named preset, perspective, or d…AfterTransfer motion from a reference video, a named animation preset or one of the account's generated animations (an `animation_id` from createAnimation or listMyAnimations) onto a static sprite image, producing an animated spritesheet that mimics the reference movement. Provide the sprite as image (URL or base64) plus either a video URL or a preset_id together with perspective and direction (all three from listAnimationPresets; if both video and preset_id are sent the video wins). The job result is the same sprite result as animateSprite: `spritesheet_url`, `video_url`, grid fields, optional GIF / frame / with-background URLs, and `audio_url` when the model is hydra. `duration` defaults to 1.5s where the chosen model offers it, otherwise to that model's shortest (hydra, the default, starts at 3s) - and a longer reference clip or preset is compressed to fit, so pass the preset's own `duration` (returned by listAnimationPresets) to keep its timing. It returns HTTP 400 if neither a video n…
- Description of
requestBodyBeforePayload for transferring motion from a
videoonto a static sprite image, producing an animated spritesheet.AfterPayload for transferring motion from a video, an animation preset or a generated animation onto a static sprite image, producing an animated spritesheet.
- Description of
Server instructions
BeforeIMPORTANT: Asset URLs returned by these tools point to Google Cloud Storage links that EXPIRE AFTER 7 DAYS. Any generated asset that needs to outlive that window — especially assets destined for production use — must be downloaded and saved locally (or re-uploaded to permanent storage) right away. Never store or hard-code the returned URLs as permanent references. Before generating with a feature you have not used here before, call searchDocs with a plain-language question to read Ludo's own guidance for it — how to pick a sprite animation mode or model, when to use Generate Before / Generate After, how margins behave, and each generator's known limitations. It returns only the few documentation sections that answer the question. Use getDocs when you need to browse what documentation exists (no arguments gives a table of contents) or to read a whole document or named sections; a whole document can run to tens of thousands of characters. If searchDocs returns no results or an error, fall back to getDocs. JOBS: every generation tool returns {id, status} immediately (except convertToPixelArt, which answers with its result directly). Poll getApiJob with that id (pass wait: 30 to long-poll; up to 60) until status is succeeded (read result - exactly the response documented for the tool) or failed (read error: {code, subcode, message, retriable}); canceled is the third terminal status. Non-terminal responses carry poll_after_ms - wait at least that long between polls. Each account may have up to 50 generations queued or running at once; beyond that a call returns 429 (PENDING_JOBS_LIMIT) - wait for jobs to finish. cancelApiJob cancels a job that is still queued. CREDITS: each tool states its price. Credits are held when a job is accepted; for duration-priced tools the final charge is rate x produced seconds (legacy models keep a minimum charge), never more than for the duration requested, and the difference - or everything, if the job fails or is cancelled - is refunded.…
AfterIMPORTANT: Asset URLs returned by these tools point to Google Cloud Storage links that EXPIRE AFTER 7 DAYS. Any generated asset that needs to outlive that window — especially assets destined for production use — must be downloaded and saved locally (or re-uploaded to permanent storage) right away. Never store or hard-code the returned URLs as permanent references. Before generating with a feature you have not used here before, call searchDocs with a plain-language question to read Ludo's own guidance for it — how to pick a sprite animation mode or model, when to use Generate Before / Generate After, how margins behave, and each generator's known limitations. It returns only the few documentation sections that answer the question. Use getDocs when you need to browse what documentation exists (no arguments gives a table of contents) or to read a whole document or named sections; a whole document can run to tens of thousands of characters. If searchDocs returns no results or an error, fall back to getDocs. JOBS: every generation tool returns {id, status} immediately (except convertToPixelArt, which answers with its result directly). Poll getApiJob with that id (pass wait: 30 to long-poll; up to 60) until status is succeeded (read result - exactly the response documented for the tool) or failed (read error: {code, subcode, message, retriable}); canceled is the third terminal status. Non-terminal responses carry poll_after_ms - wait at least that long between polls. Each account may have up to 50 generations queued or running at once; beyond that a call returns 429 (PENDING_JOBS_LIMIT) - wait for jobs to finish. cancelApiJob cancels a job that is still queued. CREDITS: each tool states its price. Credits are held when a job is accepted; for duration-priced tools the final charge is rate x produced seconds (legacy models keep a minimum charge), never more than for the duration requested, and the difference - or everything, if the job fails or is cancelled - is refunded.…
-
1 tool changed.
Details, 10 Nov 2026, 20:46 UTC
Changed 1
getPricingdescriptionBeforeWhat Ludo's paid service costs and includes, for an agent advising a user: every plan with its monthly and annual price, credits, seats, queue concurrency and what it includes or lacks; credit top-ups and their price brackets; what each API call costs; and the rules to know before telling a user to pay. The ones that matter most: the API, MCP and CLI need an active
Pro or Studioplan(Free and Indie get402 on every other call), and there every generation costs credits - "unlimited" on Pro and Studio is the web app only. Plans are bought in the web app (`links.billing`), not through the API. Plans, prices and rules here are the live ones, the same as https://ludo.ai/pricing. This is a free lookup (no credits, no job) and works with or without an API key, on any plan.AfterWhat Ludo's paid service costs and includes, for an agent advising a user: every plan with its monthly and annual price, credits, seats, queue concurrency and what it includes or lacks; credit top-ups and their price brackets; what each API call costs; and the rules to know before telling a user to pay. The ones that matter most: the API, MCP and CLI need an active paid plan (the free trial gets 402 on every other call), and there every generation costs credits - "unlimited" on Pro and Studio is the web app only. Plans are bought in the web app (`links.billing`), not through the API. Plans, prices and rules here are the live ones, the same as https://ludo.ai/pricing. This is a free lookup (no credits, no job) and works with or without an API key, on any plan.
-
1 tool added and 13 tools changed.
Details, 6 Nov 2026, 17:54 UTC
Added 1
createNormalMapWritesMake the normal map of an image, for 2.5D lighting: a lossless WebP of the same size and alpha as the image (transparent pixels are flat), in the OpenGL convention (red = right, green = up, blue = towards the viewer; Unity and Godot read it as is, Unreal expects green flipped). Pixel art gets one normal per art pixel, and the map of a seamless tile tiles the same way. An image you generated on Ludo is read with its type and pixel grid; for any other image pixel art is detected. Free, and limited to 20 calls per 5 minutes, 120 an hour and 1000 a day (HTTP 429 beyond). To get maps with new images or spritesheets, pass save_normals: true to the generation instead. The image is uploaded and validated, and an image larger than 15MB is rejected with HTTP 400. Async generation job: returns `{id, status}` - poll `getApiJob` (job and credit contract: see the server instructions).
Changed 13
adjustSpritesheetinput schemaanimateSpriteinput schemaanimateSpriteKeyframesinput schemacreateDirectionalSpritesinput schemacreateDirectionalStillsinput schemacreateImageinput schemaeditImageinput schemaeditSpritesheetinput schemageneratePoseinput schemagenerateWithStyleinput schema
rotateSpriterotateSpritesheettransferMotion -
5 tools changed.
Details, 6 Nov 2026, 14:45 UTC
Changed 5
animateSpriteinput schemaanimateSpriteKeyframesinput schemacreateImageinput schemaeditImageinput schemagenerateWithStyleinput schema
-
4 tools changed.
Details, 5 Nov 2026, 20:45 UTC
Changed 4
animateSpriteinput schemaanimateSpriteKeyframesinput schemaeditSpritesheetinput schematransferMotioninput schema
-
5 tools changed. Server instructions changed.
New server instructions
Details, 5 Nov 2026, 11:52 UTC
Changed 5
animateSpritedescription and input schemaThe text shown here is the same before and after: the change is past the first 1,000 characters or in characters that don’t show.
animateSpriteKeyframesdescription and input schemaThe text shown here is the same before and after: the change is past the first 1,000 characters or in characters that don’t show.
editSpritesheetdescription and input schemaThe text shown here is the same before and after: the change is past the first 1,000 characters or in characters that don’t show.
rotateSpritesheetinput schematransferMotioninput schema
Server instructions
BeforeIMPORTANT: Asset URLs returned by these tools point to Google Cloud Storage links that EXPIRE AFTER 7 DAYS. Any generated asset that needs to outlive that window — especially assets destined for production use — must be downloaded and saved locally (or re-uploaded to permanent storage) right away. Never store or hard-code the returned URLs as permanent references. Before generating with a feature you have not used here before, call searchDocs with a plain-language question to read Ludo's own guidance for it — how to pick a sprite animation mode or model, when to use Generate Before / Generate After, how margins behave, and each generator's known limitations. It returns only the few documentation sections that answer the question. Use getDocs when you need to browse what documentation exists (no arguments gives a table of contents) or to read a whole document or named sections; a whole document can run to tens of thousands of characters. If searchDocs returns no results or an error, fall back to getDocs. JOBS: every generation tool returns {id, status} immediately (except convertToPixelArt, which answers with its result directly). Poll getApiJob with that id (pass wait: 30 to long-poll; up to 60) until status is succeeded (read result - exactly the response documented for the tool) or failed (read error: {code, subcode, message, retriable}); canceled is the third terminal status. Non-terminal responses carry poll_after_ms - wait at least that long between polls. Each account may have up to 50 generations queued or running at once; beyond that a call returns 429 (PENDING_JOBS_LIMIT) - wait for jobs to finish. cancelApiJob cancels a job that is still queued. CREDITS: each tool states its price. Credits are held when a job is accepted; for duration-priced tools the final charge is rate x produced seconds (legacy models keep a minimum charge), never more than for the duration requested, and the difference - or everything, if the job fails or is cancelled - is refunded.…
AfterIMPORTANT: Asset URLs returned by these tools point to Google Cloud Storage links that EXPIRE AFTER 7 DAYS. Any generated asset that needs to outlive that window — especially assets destined for production use — must be downloaded and saved locally (or re-uploaded to permanent storage) right away. Never store or hard-code the returned URLs as permanent references. Before generating with a feature you have not used here before, call searchDocs with a plain-language question to read Ludo's own guidance for it — how to pick a sprite animation mode or model, when to use Generate Before / Generate After, how margins behave, and each generator's known limitations. It returns only the few documentation sections that answer the question. Use getDocs when you need to browse what documentation exists (no arguments gives a table of contents) or to read a whole document or named sections; a whole document can run to tens of thousands of characters. If searchDocs returns no results or an error, fall back to getDocs. JOBS: every generation tool returns {id, status} immediately (except convertToPixelArt, which answers with its result directly). Poll getApiJob with that id (pass wait: 30 to long-poll; up to 60) until status is succeeded (read result - exactly the response documented for the tool) or failed (read error: {code, subcode, message, retriable}); canceled is the third terminal status. Non-terminal responses carry poll_after_ms - wait at least that long between polls. Each account may have up to 50 generations queued or running at once; beyond that a call returns 429 (PENDING_JOBS_LIMIT) - wait for jobs to finish. cancelApiJob cancels a job that is still queued. CREDITS: each tool states its price. Credits are held when a job is accepted; for duration-priced tools the final charge is rate x produced seconds (legacy models keep a minimum charge), never more than for the duration requested, and the difference - or everything, if the job fails or is cancelled - is refunded.…
-
1 tool changed.
Details, 5 Nov 2026, 02:52 UTC
Changed 1
attachDirectionalAccessoriesThe 10 newest entries show every detail; older ones show names only.
-
2 tools added and 6 tools changed. Server instructions changed.
New server instructions
Details, 4 Nov 2026, 17:54 UTC
Added 2
attachDirectionalAccessoriesfitDirectionalAccessoryChanged 6
animateSpriteanimateSpriteKeyframescreateImageeditSpritesheetrotateSpritesheettransferMotionThe 10 newest entries show every detail; older ones show names only.
-
9 tools changed. Server instructions changed.
New server instructions
Details, 3 Nov 2026, 20:52 UTC
Changed 9
animate3DModelanimate3DModelPresetcreateDirectionalSpritescreateDirectionalStillscreateVideocreateVideoFromReferenceseditVideopreviewDirectionalSpritesrigModelThe 10 newest entries show every detail; older ones show names only.
-
Tracking started: 46 tools.
FAQ
Can I paste mcp.tc/i/ludo-ai-game-assets into my MCP client?
No. mcp.tc links are pages, not server addresses. Connect with https://mcp.ludo.ai/mcp, so your client talks to Ludo AI Game Assets directly. Your key goes there too, never to mcp.tc. The quick link is for sharing: it opens this page, with setup steps for every client.
Does Ludo AI Game Assets need an API key or a sign-in?
Yes. Ludo AI Game Assets needs an API key, sent as the Authorization header. Get one from Ludo.ai and keep it in your client’s config, never in a shared file.
Is Ludo AI Game Assets a remote or a local server?
Remote. Ludo.ai hosts it at https://mcp.ludo.ai/mcp, and it speaks Streamable HTTP. There’s nothing to install.
What can Ludo AI Game Assets do?
It has 54 tools, including validateApiKeyEndpoint, createImage and generateWithStyle. You can generate game art images and restyle from a reference image, animate sprites into spritesheets from prompts or keyframes and create, rig and animate 3D models.
Which clients can use it?
Any client that supports remote MCP servers and can send your key: Claude Code, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. On claude.ai and Claude Desktop, add the key as a request header when you create the custom connector. ChatGPT can’t send a key, so it can’t use it.
Does mcp.tc track changes to Ludo AI Game Assets?
Yes. Ludo AI Game Assets’s History tab shows each change we find to its tools, down to descriptions and parameters, plus new versions and edits by its owner. Follow the listing to get an email when it changes.
Who wrote this page?
mcp.tc’s robot read Ludo AI Game Assets’s own metadata (its MCP handshake, tool list and public pages), and an AI model drafted the text from it. A person reviews anything the checks can’t confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.
mcp.tc isn’t affiliated with Ludo.ai. This page was built from Ludo AI Game Assets’s public metadata, last checked on 18 Nov 2026, and an AI model wrote the description, so it can be wrong. Names and marks belong to their owners. Something off? Report this listing.