# com.spriteship/spriteship (remote · spriteship.com)

Build a game's 2D art layer with your agent: characters, animations, tilesets, levels, 5 engines.

- Trust score: 70/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-17

## Components

- remote · `spriteship.com`: 70/100 (this document), [markdown](https://verifymcp.io/servers/com-spriteship-spriteship/spriteship.md), [page](https://verifymcp.io/servers/com-spriteship-spriteship/spriteship)

## Channel facts

- Endpoint: `https://spriteship.com/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-17.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 67/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 10058 tokens (~245/item across 41 items; 41 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 10/100
  - Stability observed for 3 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http com-spriteship-spriteship https://spriteship.com/mcp
```

### Codex

```toml
[mcp_servers.com-spriteship-spriteship]
url = "https://spriteship.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-spriteship-spriteship": {
      "type": "remote",
      "url": "https://spriteship.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-spriteship-spriteship --url https://spriteship.com/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-spriteship-spriteship:
    url: "https://spriteship.com/mcp"
```

### Other

```json
{
  "mcpServers": {
    "com-spriteship-spriteship": {
      "type": "http",
      "url": "https://spriteship.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-17 (score 70, +1)

- [security] Tool “generate_character_animation” rewrote its description, which is the text the model reads
- [functional] New tool “phase_split”
- [functional] New tool “rematte_animation”
- [cosmetic] “generate_character_animation” added an optional parameter “mirrorAnims”

### 2026-08-16 (score 69, 0)

- [security] Tool “get_project” rewrote its description, which is the text the model reads

### 2026-08-15 (score 69, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-08-14 (score 68)

First indexed and scored.

## MCP tools (41)

### `whoami` (~59 tokens)

Who am I

Verify the API key and report which powers it has. Returns { userId, username, keyId, keyName, scopes }. Call this first when a tool fails with a scope error — the scopes array tells you what this key can and cannot do.

### `get_credits` (~325 tokens)

Get credit balance

Current credit balance, and optionally the recent ledger. Every ledger entry carries apiKeyId/apiKeyName so you can see exactly what THIS key spent. Check the balance before proposing any paid generation. When the balance will not cover what the user wants, say what IS affordable rather than only that they are short — "1200 for all three animations, you have 900, so two now or top up for all three" is the useful answer. Two different walls exist and they need OPPOSITE advice: running out of BALANCE is fixed by buying credits (the 402 carries a topUpUrl — send that link, never quote prices, they change), while hitting the key's DAILY SPEND CAP is not a money problem at all — the credits are already in the account, and the fixes are raising the cap or waiting for resetsAt. Never suggest a purchase for a cap trip. If the user asks HOW to raise the cap: the 403 carries capSettingsUrl — give them that link and tell them to edit the key there. YOU cannot change it, by design: the cap edit needs a logged-in session and is unreachable with an API key, because a key that could raise its own cap would not be a cap. Do not retry hoping it passes, and do not ask them to paste credentials.

Input parameters:

- `apiKeyId` (string): Filter ledger entries to one key (UUID).
- `includeLedger` (boolean): Also return recent ledger entries.
- `limit` (integer): Max items to return (default 100, max 500).

### `list_projects` (~93 tokens)

List projects

All of the user's projects: { id, name, gameType, style, itemCount, createdAt, updatedAt }. gameType (platformer / topdown / topdown_overhead / isometric / point_and_click) determines how every character and asset in the project is drawn and animated — read it before generating anything.

Input parameters:

- `limit` (integer): Max items to return (default 100, max 500).

### `get_project` (~81 tokens)

Get project

One project with its description, registered mount slots, and assetSuggestions — premade AI prompt ideas per entity type (character + the 6 asset types), tailored to the project's vision. Use them as ready-made prompts when creating characters/assets. May be null right after create (generated asynchronously — re-fetch to read).

Input parameters:

- `projectId` (string, required): Project id.

### `list_characters` (~108 tokens)

List characters

Characters with the re-sync signals: contentVersion (opaque change token — compare for equality, never parse or order), hasActiveJob, apiReady, pose/animation counts, tags, favourite. Persist contentVersion per character and re-fetch only when it changes.

Input parameters:

- `limit` (integer): Max items to return (default 100, max 500).
- `name` (string): Case-insensitive substring filter on the name.
- `projectId` (string): Restrict to one project.

### `get_character` (~87 tokens)

Get character

The full PhaserCharacter JSON: animations, frameSize, gameType, per-group atlas + spritesheet URLs, poses and mount points. Every binary URL is presigned and expires in ~1h — download immediately, never store or commit one. This is the same payload the in-app game preview consumes, so it is always a correct export.

Input parameters:

- `characterId` (string, required): Character id.

### `get_character_manifest` (~60 tokens)

Get character manifest

The self-describing export contract (tizo-export.json manifest + its JSON Schema) without downloading the zip. Use this to learn the file inventory and field meanings before wiring an export into a game project.

Input parameters:

- `characterId` (string, required): Character id.

### `list_character_poses` (~82 tokens)

List character poses

All poses on a character: { id, name, prompt, status pending|done|error, url, pendingSince, errorCode, creditsRefunded }. This is the poll target after generate_pose — pose generation has no job id. A pose still pending long after pendingSince is stalled, not working.

Input parameters:

- `characterId` (string, required): Character id.

### `list_assets` (~136 tokens)

List assets

Assets (static / tileset / staged / background / terrain / texture) with slug, hasAnimation, updatedAt, tags and favourite. hasAnimation is data-derived: ANY asset type can carry an animation, so never infer it from the type.

Input parameters:

- `limit` (integer): Max items to return (default 100, max 500).
- `name` (string): Case-insensitive substring filter on the name.
- `projectId` (string): Restrict to one project.
- `slug` (string): Exact slug match (a slug is an identifier — no partial hits).
- `type` (string): Filter by asset type.

### `get_asset` (~300 tokens)

Get asset

One asset with its revision iterations and typed animation projection. Accepts the asset id OR its slug. Texture assets carry metadata.seamless.seamMetric (a FREE wrap-edge verdict) and metadata.seamless.fixed — read seamMetric.pass to decide whether a cell needs the paid fix_asset_seams call at all. For tileset/staged/terrain the `grid` block reports how the sheet was actually cut — rows, cols, tileCount, cell size, one url per cell, and the engine-ready sidecars. After creating one, COMPARE `grid.rows`/`grid.cols`/`grid.tileCount` AGAINST THE GRID YOU REQUESTED — that comparison is the real check, because the sheet can cut wrong while the job still reports done. Do not rely on `grid.complete` alone: it only verifies the server is self-consistent (tileCount === rows × cols), so a sheet cut on dims nobody asked for still reads as complete. `grid.tiles[].url` gives you any single cell on its own if you want to look. `grid.dimsAssumed: true` means no grid was specified and the splitter invented one — treat those dims as untrustworthy. Backgrounds carry a `background` block echoing the sub-type, view and the aspect ratio actually generated — read it back to confirm the shape when you left aspectRatio unset.

Input parameters:

- `assetId` (string, required): Asset id or slug.

### `get_custom_fields` (~96 tokens)

Get custom field definitions

Typed custom-field definitions for a character or asset, plus the derived builtins ($animation for characters, $autoplay/$loop for animated assets). Per-placement VALUES ride on get_map; map exports bake resolved values and ship fields-schema.json. Read-only here — definitions are edited in the dashboard.

Input parameters:

- `entityId` (string, required): Character id, or asset id/slug.
- `kind` (string, required): Which entity table to read.

### `get_frames` (~213 tokens)

Get animation frames

Presigned per-frame thumbnails for a character animation or an asset motion pair — never inline base64. Use format:"sheet" to get ONE index-labeled contact sheet, which lets you judge a whole capture in a single look; that is the intended way to pick which frames to keep before calling select_frames.

Input parameters:

- `animation` (string): Animation slug — required when target=character.
- `entityId` (string, required): Character id (target=character) or asset id/slug (target=assetPair).
- `format` (string): "sheet" returns one labeled contact sheet.
- `indices` (string): Comma-separated frame indices to subset, e.g. "0,4,8".
- `pairId` (string): Motion pair id — required when target=assetPair.
- `size`: Max thumbnail edge (default 256, cap 1024). "full" opts out of downscaling.
- `target` (string, required): Frames of a character animation, or of an asset motion pair.

### `list_maps` (~66 tokens)

List maps

Level-editor maps with updatedAt and hasMapData. hasMapData:false means the map was never saved and cannot be exported.

Input parameters:

- `limit` (integer): Max items to return (default 100, max 500).
- `projectId` (string): Restrict to one project.

### `get_map` (~49 tokens)

Get map

A map row plus its saved level data (layers, placements, per-placement custom-field values). Returns mapData:null when the map has never been saved.

Input parameters:

- `mapId` (string, required): Map id.

### `export_map` (~73 tokens)

Export map (JSON)

Engine-ready map JSON built from the SAVED level data, with custom-field values baked in. For the zip bundle (per-tile PNGs, loader scripts, tileset files) use get_export_command instead.

Input parameters:

- `engine` (string): Target engine (default tiled).
- `mapId` (string, required): Map id.

### `get_job` (~307 tokens)

Get job status

Poll a background job. Every write tool that returns a jobId is polled here. On status:"error" the response is enriched with creditsRefunded and retryCost, so you can tell the user exactly what a retry costs. Poll every few seconds — generations routinely take minutes. THIS IS HOW YOU LEARN WHAT A CREATE CALL MADE: characterIds / assetIds list the entities this job produced — ONE normally, FOUR when create_character ran with the 2x2 variation grid — and on status:"done" characterPreviews carries a presigned image per character so you can show the user the options and let them pick. queued:true means it has not started yet (waiting for a slot) and has spent nothing. On any TERMINAL status (done or error) the response carries a `credits` block — { charged, refunded, net, balance, spendCapDaily, spentLast24h, capRemaining }. TELL THE USER `credits.net` AND `credits.balance` when the work finishes, in one short line. Report `net`, never your own pre-flight estimate: the two differ routinely — a 2x2 grid is ONE charge for four entities and failed steps are refunded — so quoting the estimate can report a cost that never happened. Do NOT attach a purchase suggestion to a successful generation; only raise buying credits when a call is actually blocked or the balance will not cover what the user asked for next.

Input parameters:

- `jobId` (string, required): Job id.

### `get_export_command` (~147 tokens)

Get export download command

Build the authenticated download URL + a ready-to-run curl line for a zip export (character engine bundle, asset bundle, or map bundle). Run the curl in your own shell — zips are multi-MB binaries and must not be passed through the model. Requires SPRITESHIP_API_KEY to be set in that shell.

Input parameters:

- `engine` (string, required): Target engine. "tiled" is maps only; sprites have no Tiled emitter.
- `entityId` (string, required): Character id, asset id/slug, or map id.
- `size` (string): Characters only — narrow a phaser zip to one downscale variant.
- `target` (string, required): What to export.

### `select_frames` (~195 tokens)

Select animation frames

FREE, no AI. Curate which frames an animation keeps, by index into the full capture, in order. Pass an empty array to reset to all frames. Non-destructive: the full capture is retained, so you can re-select at any time. Use get_frames with format:"sheet" first to choose indices. Returns a jobId — poll get_job.

Input parameters:

- `animation` (string): Animation slug — required when target=character.
- `compositing` (object): Characters only — apply scale/offset in the same rebuild.
- `entityId` (string, required): Character id (target=character) or asset id/slug (target=assetPair).
- `frames` (array, required): Ordered frame indices to keep. Empty array resets to the full capture.
- `pairId` (string): Motion pair id — required when target=assetPair.
- `target` (string, required): A character animation, or an asset motion pair.

### `duplicate_animation` (~115 tokens)

Duplicate an animation

FREE, no AI. Clone an animation under a new slug so you can curate a DIFFERENT frame subset on the copy — e.g. duplicate walk_right, then select_frames down to one frame to get a directional idle. The original is untouched. Returns a jobId — poll get_job.

Input parameters:

- `animation` (string, required): Source animation slug.
- `characterId` (string, required): Character id.
- `newId` (string): Slug for the copy ([A-Za-z0-9_-], default "<source>_copy").

### `create_animation_from_pose` (~150 tokens)

Create a 1-frame animation from a pose

FREE, no AI. Promote a pose into a real 1-frame animation (a still/idle) that is scaled to match the character's other animations and exports to every engine. Pass poseId "__idle__" to use the character's default image when it has no poses. Returns a jobId — poll get_job.

Input parameters:

- `characterId` (string, required): Character id.
- `displayName` (string): Human-facing label.
- `fps` (integer): Playback fps.
- `newId` (string): Slug for the new animation ([A-Za-z0-9_-]).
- `poseId` (string, required): Pose id, or "__idle__" for the character's default image.

### `set_asset_runtime_intent` (~175 tokens)

Set an asset's runtime render intent

FREE and SYNCHRONOUS (no jobId — do not poll). Declare how an asset revision should be rendered at runtime: plain_image, particle_emitter, deformable_strip, repeat_fill, nine_slice, shader_effect or path_follow. The intent and its config flow into every engine export made AFTER this edit. Set tileIndex to target one tile of a tileset/staged asset.

Input parameters:

- `assetId` (string, required): Asset id or slug.
- `config` (object): Intent-specific config. Validated and clamped server-side; unknown keys are dropped.
- `iterationId` (string, required): Revision (iteration) id to stamp.
- `runtimeUse` (string, required): The render intent. plain_image clears any previous intent.
- `tileIndex` (integer): Target one tile (tileset/staged only).

### `cancel_job` (~55 tokens)

Cancel a job

FREE. Abort a running job. Outstanding credit charges for the aborted work are refunded automatically. Use this when a generation is clearly going wrong rather than letting it run to completion.

Input parameters:

- `jobId` (string, required): Job id to cancel.

### `frame_animation` (~251 tokens)

Animate a grid asset from its own tiles

FREE, and NO AI AT ALL — no video model, no credits, nothing to approve. The tiles of a tileset/staged asset ARE the frames: give the tile indices in playback order (repeats allowed) and they are composited into a real spritesheet animation on that asset, exportable to every engine. This is how you animate a coin flip, a flickering torch or a chest opening WITHOUT paying for image-to-video. Try this before animate_asset whenever the motion already exists across the tiles. Returns a jobId — poll get_job.

Input parameters:

- `assetId` (string, required): Asset id or slug (must be a grid asset: tileset or staged).
- `fps` (integer): Playback fps (1-30, default 12).
- `frameIndices` (array, required): Tile indices in playback order, e.g. [0,1,2,3,2,1]. At least 2, at most 120. Repeats are allowed — that is how you hold or ping-pong a frame.
- `iterationId` (string, required): Revision (iteration) id whose tiles are the frames.
- `name` (string): Label for the animation (default "Frames").

### `rebuild_character` (~141 tokens)

Rebuild a character from its cached frames

FREE, no AI. Re-render every spritesheet, atlas and export of a character from its durable cached frames. This is the repair/refresh tool: use it when a sheet looks stale or wrong after a series of edits, or when a previous rebuild failed. It never re-generates art, so it cannot change what the character looks like — only how the frames are packed and normalized. Always rebuilds ALL animations: heights are normalized ACROSS animations, so rebuilding a subset would size that subset against itself and make animations drift apart on screen. Takes no options. Returns a jobId — poll get_job.

Input parameters:

- `characterId` (string, required): Character id.

### `mirror_animation` (~132 tokens)

Mirror an animation horizontally

FREE, no AI. Flip every cached frame of ONE animation horizontally and rebuild it — the cheap way to get walk_left from walk_right. NOT idempotent: calling it twice flips the animation back to its original orientation, so call it once and check the result before calling again. Frame count and order are preserved, so any frame selection stays valid. To keep BOTH directions, call duplicate_animation first and mirror the copy. Returns { jobId, mirrored } (frames flipped) — poll get_job.

Input parameters:

- `animation` (string, required): Animation slug to flip in place.
- `characterId` (string, required): Character id.

### `rematte_animation` (~192 tokens)

Fix an animation's edge artifacts (re-matte)

FREE, no AI. Try a cleaner background removal on ONE animation's source video — the repair for a quality read showing deliveredIssues containing "matte" (green fringe, flickering holes, ragged edges). The cleaner version is kept ONLY if it measures better, so this can never make the animation worse; the motion itself is unchanged. One attempt per capture: if the same frames were already tried (matteRepair stamp), a repeat call is a cheap re-check + free re-render — regenerate the animation for a fresh take instead. Fails with SOURCE_VIDEO_EXPIRED when the source video aged past its 30-day retention. Returns { jobId } — poll get_job, then re-read the character's quality block: "matte" gone = the cleaner version shipped.

Input parameters:

- `animation` (string, required): Animation slug to re-matte in place.
- `characterId` (string, required): Character id.

### `phase_split` (~174 tokens)

Split an animation into game phases

FREE, no AI. Carve ONE multi-state clip into separate game-phase animations by frame windows — the classic case is a jump becoming crouch/rise/fall/land, with fall looping while airborne and the rest playing once. Each phase becomes a real exportable animation; the source animation is untouched. Jump-family animations often carry a ready-made suggestion: get_character → animations[<anim>].phaseProposal — pass its phases through verbatim. Frame windows index the FULL capture. Returns { jobId, created } — poll get_job.

Input parameters:

- `animation` (string, required): Source animation slug (e.g. "jump").
- `characterId` (string, required): Character id.
- `phases` (array, required): 2-6 phase windows. animations[<anim>].phaseProposal from get_character usually supplies these verbatim.

### `reprocess_asset` (~281 tokens)

Re-cut a grid asset's tiles

FREE and SYNCHRONOUS (no jobId — do not poll), no AI. Re-run the grid split on a tileset or staged asset revision using its STORED original image, so you can change how the sheet is CUT without paying for a new generation: anchor (where each sprite sits in its cell), per-cell nudges, and a per-cell inset. Omitted fields keep the revision's current values; send cellOffsets:[] or cellInset:0 to clear. tileset and staged ONLY — other types have no grid, and terrain has no re-cut path at all (it is alpha-split from one sheet; iterate it with revise_asset instead). Returns a grid summary; call get_asset afterwards for fresh presigned tile URLs.

Input parameters:

- `anchor` (string): Where each sprite is placed inside its cell. "bottom-middle" is the default for sprites that stand on the ground.
- `assetId` (string, required): Asset id or slug (tileset or staged).
- `cellInset` (integer): Pixels shaved off every side of each cell, to drop neighbouring bleed (0-32). Pass 0 to clear.
- `cellOffsets` (array): Per-cell pixel nudges, in tile-index order. Pass [] to clear all nudges.
- `iterationId` (string, required): Revision (iteration) id to re-cut.

### `create_project` (~222 tokens)

Create a project

FREE and SYNCHRONOUS (no jobId — do not poll). Creates the container everything else needs: characters and assets are created INSIDE a project, and the project's gameType is what decides how they are drawn and animated. Also seeds a starter level map, so the game preview has something real to render immediately. Call list_projects first — reuse an existing project rather than making a near-duplicate.

Input parameters:

- `description` (string): Optional project description. Feeds the prompt context for later generations.
- `gameType` (string, required): REQUIRED and permanent for everything in the project. platformer = side view with gravity; topdown = 4/8-direction overhead-ish (Zelda-like); topdown_overhead = straight down; isometric = 2:1 diamond…
- `name` (string, required): Project name shown in the dashboard.
- `style` (string): Optional art-style id applied as the default for generations in this project.

### `create_character` (~600 tokens)

Create a character

PAID (~150 credits). Generate a NEW character from a text prompt. This is the entry point for building art from nothing — call create_project first if the user has no project. IMAGE ONLY: it produces the character still, not animations. Animation is a separate explicit step (generate_character_animation for a walk cycle, generate_character_turn for the 360 rotation), because animating costs several times more and the user should choose it. SET gridRows:2 AND gridCols:2 TO GET FOUR DESIGN VARIATIONS FOR THE SAME PRICE — one image call is split into four separate characters. That is almost always the right call for a first attempt: show the user all four and let them pick. Returns { jobId, expectedCharacterCount } — poll get_job; on status:"done" its characterIds and characterPreviews tell you which characters exist and what they look like. gameType is inherited from the project, never passed here (isometric projects create TOP-DOWN characters — the working directional pipeline; the character reads gameType:"topdown" afterwards). DEFAULTS TO A COST PREVIEW — see the dryRun argument.

Input parameters:

- `cameraAngle` (number): Camera elevation in degrees — only meaningful for angled top-down projects.
- `characterImageSize` (string): Aspect ratio of the generated image. Omit for the game-type default.
- `dryRun` (boolean): DEFAULTS TO TRUE. While true this returns only a cost quote ({ estimatedCredits, balance, spendCapDaily, spentLast24h, capRemaining }) and executes nothing. Show the user estimatedCredits and get an…
- `gridCols` (number): Set to 2 together with gridRows:2 for the 4-variation grid.
- `gridRows` (number): Set to 2 together with gridCols:2 for the 4-variation grid. Same cost as one image.
- `idempotencyKey` (string): Optional Idempotency-Key for the real (dryRun:false) call. Omit and one is minted per call. Reuse the SAME value when retrying a call that failed with ENTITY_BUSY / 402 / 429 so the retry cannot doub…
- `imageModel` (string): Override the image model. Omit unless the user asked for a specific one.
- `projectId` (string, required): REQUIRED. The project the character belongs to — it supplies gameType and the default style.
- `prompt` (string, required): What the character is, e.g. "a plague doctor with a lantern". Describe the subject, not the art style.
- `referenceAssetUrls` (array): URLs of existing images to steer the design. URLs only — base64 is rejected by the API.
- `style` (string): Art-style override. Omit to inherit the project's style — usually correct, since a project should look consistent.

### `generate_character_animation` (~587 tokens)

Generate character animations

PAID, and the cost MULTIPLIES BY THE NUMBER OF ANIMATIONS (each is its own image-to-video call, ~400 credits at defaults). This is real motion — a walk cycle, an attack, an idle bob — not the 1-frame still that create_animation_from_pose produces. Read the character's gameType and use the standard animation names for it (get_character shows what already exists); a name that already exists is REGENERATED. Ask the user which animations they want before spending: 4 animations cost 4x. If the character came from a 2x2 create, there are FOUR siblings and animating is per-character: show the user the characterPreviews from get_job and have them pick one before you spend. For multi-direction sets, mirrorAnims gives you FREE flipped copies of a direction generated in the same call (walk_left from walk_right) — prefer a real generation when the character is asymmetric, because a held item switches sides under a mirror. Returns { jobId, animations } — poll get_job. A prompt that composes too long for the model is rejected with PROMPT_TOO_LONG before anything is charged, and the response names the animation to shorten. DEFAULTS TO A COST PREVIEW — see the dryRun argument.

Input parameters:

- `animDurations` (object): Per-animation clip length in seconds (2-10). Longer clips cost more.
- `animPrompts` (object): Per-animation extra guidance, keyed by animation slug. Folded into that animation's composed prompt.
- `animations` (array, required): Animation slugs to generate, e.g. ["walk_right","idle"]. REQUIRED — each one is a separate paid video call.
- `characterId` (string, required): Character id.
- `customAnims` (object): Define animations that are NOT part of the game type's standard set, keyed by the new slug.
- `dryRun` (boolean): DEFAULTS TO TRUE. While true this returns only a cost quote ({ estimatedCredits, balance, spendCapDaily, spentLast24h, capRemaining }) and executes nothing. Show the user estimatedCredits and get an…
- `idempotencyKey` (string): Optional Idempotency-Key for the real (dryRun:false) call. Omit and one is minted per call. Reuse the SAME value when retrying a call that failed with ENTITY_BUSY / 402 / 429 so the retry cannot doub…
- `mirrorAnims` (object): FREE mirrored copies, keyed newName → sourceName (e.g. { "walk_left": "walk_right" }). The source must be in this call's animations list; its fresh frames are flipped in the same job at no extra cost.
- `videoModel` (string): Override the video model.

### `generate_character_turn` (~421 tokens)

Generate a 360 turn animation

PAID (~400 credits — ONE 2-second rotation video). Spins the character through a full 360 so the sprite exists from every side; its frames are also what the directional-pose extractor reads, which is what makes top-down characters usable in more than one facing (isometric projects use top-down characters). ONLY topdown and isometric characters are supported — any other game type errors 400 TURN_NOT_SUPPORTED (topdown_overhead: the engine rotates the sprite image; platformer/point_and_click: side/front views, mirror instead). Lands as the animation "turn", or "turn_<seedPoseId>" when seeded from a pose. It 409s (ANIMATION_EXISTS) if that animation already exists — pass regenerate:true to replace it, which also clears the cached frames so you actually get new output. It also 409s (ENTITY_BUSY) while ANY other job is running on the character, because it rebuilds the spritesheet: poll that job first. Returns { jobId, animation } — poll get_job. DEFAULTS TO A COST PREVIEW — see the dryRun argument.

Input parameters:

- `characterId` (string, required): Character id.
- `dryRun` (boolean): DEFAULTS TO TRUE. While true this returns only a cost quote ({ estimatedCredits, balance, spendCapDaily, spentLast24h, capRemaining }) and executes nothing. Show the user estimatedCredits and get an…
- `idempotencyKey` (string): Optional Idempotency-Key for the real (dryRun:false) call. Omit and one is minted per call. Reuse the SAME value when retrying a call that failed with ENTITY_BUSY / 402 / 429 so the retry cannot doub…
- `regenerate` (boolean): Replace an existing turn animation instead of failing with ANIMATION_EXISTS.
- `seedPoseId` (string): Rotate a specific DONE pose instead of the character's default image. Lands as "turn_<poseId>".

### `generate_pose` (~278 tokens)

Generate a character pose

PAID (~150 credits). Generate a new pose for a character from a text description. DEFAULTS TO A COST PREVIEW — see the dryRun argument. Returns { poseId } once executed; poses have no jobId, so poll list_character_poses until status is done or error.

Input parameters:

- `characterId` (string, required): Character id.
- `dryRun` (boolean): DEFAULTS TO TRUE. While true this returns only a cost quote ({ estimatedCredits, balance, spendCapDaily, spentLast24h, capRemaining }) and executes nothing. Show the user estimatedCredits and get an…
- `idempotencyKey` (string): Optional Idempotency-Key for the real (dryRun:false) call. Omit and one is minted per call. Reuse the SAME value when retrying a call that failed with ENTITY_BUSY / 402 / 429 so the retry cannot doub…
- `imageModel` (string): Override the image model.
- `name` (string, required): Short pose name, e.g. "casting".
- `poseDescription` (string, required): What the character should be doing, e.g. "kneeling, shield raised".
- `referencePoseId` (string): Seed from an existing DONE pose instead of the base image.

### `animate_asset` (~461 tokens)

Animate an asset

PAID (image-to-video, cost scales with duration × pair count). Animate ANY asset type — the animation lands on the source asset and its still image is preserved. For grid assets (tileset/staged) pass pairs of tile indices; a self-loop { from: n, to: n } makes one tile loop seamlessly. ASK THE USER WHICH STAGES FIRST. Call get_asset, describe the tiles you can see, and get an explicit answer on which is the START and which is the END before you spend. "Animate the treasure box" does not tell you whether they mean closed→open, open→closed, or the lid alone, and guessing wrong bills them for a clip they cannot use. The server rejects a grid animate with no pairs (400) precisely so that this choice is always made deliberately — do not satisfy it by defaulting to 0→last. DEFAULTS TO A COST PREVIEW — see the dryRun argument. Returns { jobId } — poll get_job.

Input parameters:

- `assetId` (string, required): Asset id or slug.
- `closeLoop` (boolean): Single-image assets — reuse the start frame as the end frame so the clip loops.
- `dryRun` (boolean): DEFAULTS TO TRUE. While true this returns only a cost quote ({ estimatedCredits, balance, spendCapDaily, spentLast24h, capRemaining }) and executes nothing. Show the user estimatedCredits and get an…
- `durationSeconds` (number): Clip length, clamped server-side to 2-10s.
- `idempotencyKey` (string): Optional Idempotency-Key for the real (dryRun:false) call. Omit and one is minted per call. Reuse the SAME value when retrying a call that failed with ENTITY_BUSY / 402 / 429 so the retry cannot doub…
- `iterationId` (string, required): Revision (iteration) id to animate.
- `motionHint` (string): Extra motion guidance folded into the prompt.
- `pairs` (array): Grid assets only — which tile transitions to animate. Omit for single-image assets.
- `videoModel` (string): Override the video model.

### `revise_asset` (~324 tokens)

Revise an asset

PAID. Generate a new revision of an asset from feedback text. The previous revision is kept — revisions are additive, never destructive. Terrain assets also accept templateId to pull a whole category pack (edges / grounds / props / slopes / textures / structures). DEFAULTS TO A COST PREVIEW — see the dryRun argument. Returns { jobId } — poll get_job.

Input parameters:

- `assetId` (string, required): Asset id or slug.
- `dryRun` (boolean): DEFAULTS TO TRUE. While true this returns only a cost quote ({ estimatedCredits, balance, spendCapDaily, spentLast24h, capRemaining }) and executes nothing. Show the user estimatedCredits and get an…
- `idempotencyKey` (string): Optional Idempotency-Key for the real (dryRun:false) call. Omit and one is minted per call. Reuse the SAME value when retrying a call that failed with ENTITY_BUSY / 402 / 429 so the retry cannot doub…
- `imageModel` (string): Override the image model.
- `prompt` (string): What to change. Required unless templateId is given (terrain).
- `sourceIterationId` (string): Revise from a specific earlier revision instead of the current one.
- `templateId` (string): Terrain only — generate a focused category pack.
- `textureKind` (string): Texture only — 4-way seamless fill, or a directional left-right strip. Defaults to the asset's existing kind.

### `regen_asset_pair` (~284 tokens)

Regenerate one asset motion pair

PAID (~400 credits at defaults). Re-run video generation for a SINGLE motion pair of an animated asset, leaving its other pairs alone. The new take lands as an additional iteration on that pair — earlier takes are preserved. DEFAULTS TO A COST PREVIEW — see the dryRun argument. Returns { jobId } — poll get_job.

Input parameters:

- `assetId` (string, required): Asset id or slug.
- `dryRun` (boolean): DEFAULTS TO TRUE. While true this returns only a cost quote ({ estimatedCredits, balance, spendCapDaily, spentLast24h, capRemaining }) and executes nothing. Show the user estimatedCredits and get an…
- `durationSeconds` (number): Informs the cost estimate only — the dispatched job uses the pair's own duration.
- `idempotencyKey` (string): Optional Idempotency-Key for the real (dryRun:false) call. Omit and one is minted per call. Reuse the SAME value when retrying a call that failed with ENTITY_BUSY / 402 / 429 so the retry cannot doub…
- `motionPrompt` (string): Replacement motion prompt for this take.
- `pairId` (string, required): Motion pair id (from get_asset).
- `videoModel` (string): Override the video model.

### `fix_asset_seams` (~277 tokens)

Fix a texture's seams

PAID (~100 credits, one image-to-image call). Make a texture tile seamlessly. Textures are created as raw grid cells, so CHECK get_asset first: metadata.seamless.seamMetric.pass is a FREE verdict on whether this cell already tiles cleanly, and metadata.seamless.fixed tells you if it was already fixed. Do not spend on a cell that passes. The fix lands as a new current revision. DEFAULTS TO A COST PREVIEW — see the dryRun argument. Returns { jobId } — poll get_job.

Input parameters:

- `assetId` (string, required): Texture asset id or slug.
- `dryRun` (boolean): DEFAULTS TO TRUE. While true this returns only a cost quote ({ estimatedCredits, balance, spendCapDaily, spentLast24h, capRemaining }) and executes nothing. Show the user estimatedCredits and get an…
- `idempotencyKey` (string): Optional Idempotency-Key for the real (dryRun:false) call. Omit and one is minted per call. Reuse the SAME value when retrying a call that failed with ENTITY_BUSY / 402 / 429 so the retry cannot doub…
- `iterationId` (string, required): Revision (iteration) id to fix.

### `create_asset` (~1264 tokens)

Create an asset

tileset and staged REQUIRE gridRows+gridCols (e.g. 4x4) — ask the user how many tiles or stages they want. PAID (one image call). Creates a NEW asset from a prompt, in any of the six types: static (a single sprite/prop), tileset (a grid of tiles), staged (one subject in N stages, the input to animate_asset), background (scenery), terrain (a 3×3 auto-tiling sheet), texture (a seamless material). projectId is REQUIRED — the project supplies gameType, which decides how the art is drawn, and keeps the asset findable in the web app. Set gridRows:2 + gridCols:2 on a static asset to get FOUR variations for the price of ONE call; texture always produces four. A fan-out create returns one jobId — the four asset ids appear in get_job as gridAssetIds once the job finishes. Terrain has NO per-tile edit path: revising a terrain asset regenerates the whole sheet. DEFAULTS TO A COST PREVIEW — see the dryRun argument. Returns { jobId, assetId } — poll get_job. For tileset and staged, finish by calling get_asset and checking `grid.complete`: a grid sheet can cut wrong while the job still reports done, and that is the only place it shows up.

Input parameters:

- `aspectRatio` (string): BACKGROUND only — OPTIONAL, and best left unset: the server applies the recommended ratio for the chosen sub-type (e.g. 21:9 for a parallax layer, 1:1 for a ground fill), which is what the web wizard…
- `assetType` (string, required): static = one sprite/prop; tileset = a grid of related tiles; staged = one subject in N progressive stages (the input animate_asset expects); background = scenery, never a game object; terrain = auto-…
- `backgroundResolution` (string): BACKGROUND only — output tier (default 2K). 4K costs more.
- `bgType` (string): REQUIRED for assetType "background" — the sub-type, and it must be legal for the view: platformer → parallax_far/parallax_mid/parallax_near/platform_scene/static_backdrop/scrolling_backdrop; topdown…
- `bgViewType` (string): BACKGROUND only — which view the background is drawn for. Defaults to the project gameType.
- `dryRun` (boolean): DEFAULTS TO TRUE. While true this returns only a cost quote ({ estimatedCredits, balance, spendCapDaily, spentLast24h, capRemaining }) and executes nothing. Show the user estimatedCredits and get an…
- `gridCols` (integer): Grid columns — see gridRows.
- `gridRows` (integer): REQUIRED for tileset and staged — they are split into a grid, and without it the image is generated ungridded and every tile comes out cut. Optional elsewhere; on static, 2x2 means four variations fr…
- `idempotencyKey` (string): Optional Idempotency-Key for the real (dryRun:false) call. Omit and one is minted per call. Reuse the SAME value when retrying a call that failed with ENTITY_BUSY / 402 / 429 so the retry cannot doub…
- `imageModel` (string): Override the image model.
- `name` (string): Display name (defaults to the prompt).
- `perspective` (string): TERRAIN only — camera perspective. Defaults from the project gameType.
- `projectId` (string, required): REQUIRED. Owning project (create_project / list_projects). Supplies gameType + default style.
- `prompt` (string, required): What to generate. Describe the subject, not the art style — style comes from the project.
- `referenceAssetUrls` (array): Up to 4 reference image URLs to condition the generation. URLs only — raw base64 is rejected on this surface.
- `runtimeUse` (string): STATIC only (texture is locked to repeat_fill server-side). Declares how the art is meant to be rendered — particle_emitter, deformable_strip, nine_slice, shader_effect, path_follow — which changes t…
- `slug` (string): Stable handle used by every /assets/:id call ([a-z0-9-]). Auto-derived from the name when omitted.
- `style` (string): Override the project's art style for this asset only.
- `targetTileSize` (integer): Output tile side in px (16-512).
- `textureKind` (string): TEXTURE only — fill = uniform material tiling in all directions (walls/floors/ground); strip = has a directional top surface and repeats left↔right (platformer platforms). Defaults per gameType. Crea…
- `tileSize` (number): TERRAIN only — output tile size in px (64, 128 or 256).

### `retry_job` (~326 tokens)

Retry a failed job

PAID (only for the sub-steps that still need to run). Re-runs the FAILED step of a job whose status is "error" — the prompt, model and every setting are already on the job, so this is the cheap way out of a failure instead of creating the whole thing again. Work that already succeeded is NOT redone or re-charged: a generation that failed after its image landed reuses the paid result. get_job on an errored job reports retryCost, and the dryRun quote here is that same number. A non-retryable phase answers 400 JOB_NOT_RETRYABLE — some late phases hold partially-committed state and deliberately have no blanket retry. DEFAULTS TO A COST PREVIEW — see the dryRun argument. Returns { jobId } — poll get_job.

Input parameters:

- `dryRun` (boolean): DEFAULTS TO TRUE. While true this returns only a cost quote ({ estimatedCredits, balance, spendCapDaily, spentLast24h, capRemaining }) and executes nothing. Show the user estimatedCredits and get an…
- `idempotencyKey` (string): Optional Idempotency-Key for the real (dryRun:false) call. Omit and one is minted per call. Reuse the SAME value when retrying a call that failed with ENTITY_BUSY / 402 / 429 so the retry cannot doub…
- `jobId` (string, required): Id of a job whose status is "error" (from get_job).

### `generate_project_vision` (~346 tokens)

Generate a project creative brief

PAID but very cheap (one Gemini call) and SYNCHRONOUS — the result comes back in this response, there is no jobId to poll. Turns a rough game idea into { aiVision, aiPromptGuidance, aiNegativeGuidance }: a written creative direction plus the positive/negative guidance to reuse in later prompts, which is what keeps a whole project visually consistent instead of every asset drifting. Stores NOTHING — feed the wording into create_project (description/style) and into your own prompts. DEFAULTS TO A COST PREVIEW — see the dryRun argument.

Input parameters:

- `description` (string): The idea in the user's own words: setting, mood, mechanics.
- `dryRun` (boolean): DEFAULTS TO TRUE. While true this returns only a cost quote ({ estimatedCredits, balance, spendCapDaily, spentLast24h, capRemaining }) and executes nothing. Show the user estimatedCredits and get an…
- `gameType` (string, required): The view the game is played in — the brief is written for it.
- `idempotencyKey` (string): Optional Idempotency-Key for the real (dryRun:false) call. Omit and one is minted per call. Reuse the SAME value when retrying a call that failed with ENTITY_BUSY / 402 / 429 so the retry cannot doub…
- `name` (string, required): Working title of the game.
- `references` (array): Up to 6 tagged reference images the model can look at.
- `style` (string): Art style, if the user already has one in mind.

### `suggest_motion_hint` (~277 tokens)

Suggest a motion hint for a staged asset

PAID but very cheap (one Gemini call) and SYNCHRONOUS — returns { hint, cost } inline, no jobId. Reads a STAGED asset's prompt plus the stage pairs you intend to animate and writes the one-sentence motion description to pass as animate_asset's motionHint. Use it when you are about to spend ~400 credits on video and are unsure what to write: a few credits here protects that spend. Staged assets only — any other type answers 400.

Input parameters:

- `assetId` (string, required): Staged asset id or slug.
- `dryRun` (boolean): DEFAULTS TO TRUE. While true this returns only a cost quote ({ estimatedCredits, balance, spendCapDaily, spentLast24h, capRemaining }) and executes nothing. Show the user estimatedCredits and get an…
- `idempotencyKey` (string): Optional Idempotency-Key for the real (dryRun:false) call. Omit and one is minted per call. Reuse the SAME value when retrying a call that failed with ENTITY_BUSY / 402 / 429 so the retry cannot doub…
- `pairs` (array): The stage transitions you plan to animate — context for the hint, nothing is generated from them.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-spriteship-spriteship/spriteship#diagnostics

## Score history

- 2026-08-17: 70
- 2026-08-16: 69
- 2026-08-15: 69
- 2026-08-14: 68

## Links

- Remote endpoint: https://spriteship.com/mcp
- Authorisation metadata: https://spriteship.com/.well-known/oauth-protected-resource/mcp
- Website: https://spriteship.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-spriteship-spriteship/spriteship.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-spriteship-spriteship/spriteship.json
- HTML version of this page: https://verifymcp.io/servers/com-spriteship-spriteship/spriteship