Game Development

spriteship.com

Manages game development projects and characters, including credits, project details, and character synchronization signals.

1 endpoint68 known toolsFirst detected August 15, 2026Last detected September 15, 2026

ENDPOINT 1

https://spriteship.com/mcp

No auth detected

MCP server metadata

Name: spriteship
Version: 1.1.0

Capabilities

tools

Server instructions

SpriteShip generates 2D game art (characters with animated spritesheets, tilesets, terrain, brushable Materials, backgrounds, levels) and exports it to Phaser, Godot, Unity, GameMaker, Tiled, Sparrow XML character atlases, and Unreal/Paper2D (beta). Unreal is visual import, not automatic gameplay; native Unreal verification is pending. RIGHTS: use only content the user owns or has permission to use and distribute. If rights to reference images, artwork, fonts, music or code are unclear, ask before using them and offer an original alternative. Do not source third-party game assets or imitate protected branding as a shortcut. Preserve required licenses and notices. Format compatibility grants no third-party content or trademark rights and implies no endorsement. Use neutral Sparrow XML labels; fnf remains the stable technical identifier. SKILL UPDATES: the current customer skill is 0.3.5. Once when starting SpriteShip work in a session, use get_integration_status if available, with the version actually read from local SpriteShip instructions (omit when unknown). If update_available, tell the user once what changed and link the returned updateGuidePath on this configured SpriteShip server. If unknown, briefly offer the current skill and /docs/agent-skill#updates; do not claim their installed copy is outdated. A newer local copy must not be downgraded. Checks are advisory: continue compatible work if offline or unavailable, do not retry repeatedly, change files, or infer consent to update. Reconnect/refresh the client's tool catalog after server updates; this server does not push updates into existing sessions. SPENDING: tools marked PAID cost the user real money. They default to dryRun:true, which returns a cost quote and generates nothing. Never pass dryRun:false until you have shown the user estimatedCredits from a dryRun call and they have approved that specific amount in this conversation. A request to "generate something" starts that approval flow — it is not itself approval. WORKING WITH RESULTS: binary URLs are presigned and expire in about an hour — download them immediately, and never store or commit one. Characters and UI packs change-track via the opaque contentVersion token (compare for equality only); projects, assets and maps use updatedAt. For UI packs use the downloaded archive token and saved engine/selection in plan_sync; keep the existing local folder. UI requests use UI Pack tools directly, not character creation. Read the project style guide first; adopting its changes into an existing pack is explicit and never regenerates saved art. Packs provide artwork/components, not game logic or UI placement in Game Preview. Most write tools return a jobId to poll with get_job; generate_pose has no job and is polled with list_character_poses instead. Generations take minutes, not seconds. For a character animation job, status:"done" is pipeline completion only: follow its animationQualityGate to get_character and do not export, sync, or claim readiness until every affected animation is ready or you have reported the unresolved review to the user. Prefer the free tools where they do the job: frame curation, duplicating an animation, and promoting a pose to a still are no-AI operations that never touch the ledger.

Known tools 68

get_integration_status

Free advisory version check.

Inferred read-only

whoami

Verify the API key and report which powers it has.

Inferred read-only

get_credits

Current credit balance, and optionally the recent ledger.

Inferred read-only

list_projects

All of the user's projects: { id, name, gameType, style, itemCount, createdAt, updatedAt }.

Inferred read-only

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.

Inferred read-only

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.

Inferred read-only

plan_sync

Compare the versions in assets/spriteship/spriteship.

Inferred read-only

get_character

The full PhaserCharacter JSON: animations, frameSize, gameType, per-group atlas + spritesheet URLs, poses and mount points.

Inferred read-only

get_character_manifest

The self-describing export contract (tizo-export.

Inferred read-only

list_character_poses

All poses on a character: { id, name, prompt, status pending|done|error, url, direction, pendingSince, errorCode, creditsRefunded }.

Inferred read-only

list_assets

Assets (Object / Object Collection / staged / background / Environment Kit / Terrain Materials) with slug, hasAnimation, updatedAt, tags and favourite.

Inferred read-only

get_asset

One asset with its revision iterations and typed animation projection.

Inferred read-only

get_custom_fields

Typed custom-field definitions for a character or asset, plus the derived builtins ($animation for characters, $autoplay/$loop for animated assets).

Inferred read-only

get_frames

Presigned per-frame thumbnails for a character animation or an asset motion pair — never inline base64.

Inferred read-only

list_maps

Level-editor maps with updatedAt and hasMapData.

Inferred read-only

get_map

A map row plus its saved level data.

Inferred read-only

export_map

Engine-ready map JSON built from the SAVED level data, preserving placement name/gameplayId and baking custom-field values.

Inferred read-only

get_job

Poll a background job.

Inferred read-only

get_export_command

Build the authenticated download URL + a ready-to-run curl line for a zip export (character engine bundle, asset bundle, or map bundle).

Inferred read-only

select_frames

FREE, no AI.

Inferred read-only

duplicate_animation

FREE, synchronous, no AI.

Inferred read-only

create_animation_from_pose

FREE, no AI.

Inferred read-only

set_asset_runtime_intent

FREE and SYNCHRONOUS (no jobId — do not poll).

Inferred read-only

set_asset_collision_body

FREE and SYNCHRONOUS (no jobId — do not poll).

Inferred read-only

cancel_job

FREE.

Inferred read-only

approve_directional_poses

FREE approval checkpoint.

Inferred read-only

frame_animation

FREE, and NO AI AT ALL — no video model, no credits, nothing to approve.

Inferred read-only

rebuild_character

FREE, no AI.

Inferred read-only

mirror_animation

FREE, no AI.

Inferred read-only

rematte_animation

FREE, no AI.

Inferred read-only

phase_split

FREE, no AI.

Inferred read-only

reprocess_asset

FREE and SYNCHRONOUS (no jobId — do not poll), no AI.

Inferred read-only

create_project

FREE and SYNCHRONOUS (no jobId — do not poll).

Inferred read-only

create_character

PAID (~150 credits).

Inferred read-only

generate_character_animation

PAID, and the cost MULTIPLIES BY THE NUMBER OF ANIMATIONS (each is its own image-to-video call, ~400 credits at defaults).

Inferred read-only

generate_character_turn

PAID (~400 credits — ONE 2-second rotation video), except retrying the exact failed job is FREE while its provider task/result or validated stored source survives.

Inferred read-only

generate_pose

PAID (~150 credits).

Inferred read-only

animate_asset

PAID (image-to-video, cost scales with duration × pair count).

Inferred read-only

revise_asset

PAID.

Inferred read-only

regen_asset_pair

PAID (~400 credits at defaults).

Inferred read-only

convert_texture_to_material

FREE and SYNCHRONOUS, no AI.

Inferred read-only

fix_asset_seams

LEGACY ONLY; new Brushable Materials reject this operation because they use world-space sampling.

Inferred read-only

create_asset

PAID (one image call).

Inferred read-only

retry_job

FREE when the original KIE task or a validated stored artifact can be recovered; otherwise PAID only for the sub-steps that still need to run.

Inferred read-only

generate_project_vision

PAID but very cheap (one Gemini call) and SYNCHRONOUS — the result comes back in this response, there is no jobId to poll.

Inferred read-only

suggest_motion_hint

PAID but very cheap (one Gemini call) and SYNCHRONOUS — returns { hint, cost } inline, no jobId.

Inferred read-only

get_subscription_allowances

Read the currently enabled subscriber benefits and their separate monthly limits, caps and balances.

Inferred read-only

retry_unusable_result

Quality Retry is the subscription compensation for AI art that invents details, ignores the request, or arrives unusable, letting the user try again without asking support for a credit refund.

Potential side effects

import_asset_image

Import ONE still PNG or WebP as an Object or Character using one separate import allowance (Studio unlimited), zero credits.

Inferred read-only

list_ui_packs

List owned UI Packs, optionally within a project.

Inferred read-only

get_ui_pack

Read components, immutable revisions, capabilities, fonts and batch progress.

Inferred read-only

get_ui_pack_batch_recovery

Read original PNG dimensions, expiring image URL, source hash, and exact delivered/missing slots for an illustrated batch needing review.

Inferred read-only

recover_ui_pack_components

Crop missing slots from a retained original PNG after visual review.

Inferred read-only

get_ui_pack_batch

Read one paid batch and retained source URL; provider completion does not prove usable component delivery.

Inferred read-only

list_ui_fonts

Read the retained licensed Google Fonts catalog.

Inferred read-only

get_project_style_guide

Read the current guide; old projects without an adopted guide receive an initial suggestion.

Inferred read-only

save_project_style_guide

Adopt a new immutable guide revision with optimistic concurrency.

Inferred read-only

suggest_project_style

Suggest palette, treatment and existing font IDs from the available catalog.

Inferred read-only

create_ui_pack

Create an empty project-owned UI Pack with its guide snapshot.

Potential side effects

save_ui_pack_style

Save a pack-specific style for future quotes using the current pack updatedAt.

Inferred read-only

validate_ui_component_layout

Revalidate an exact current revision and apply only proven deterministic runtime layout repairs, including bar fill openings, panel text/slice regions, and explicitly named SVG button-state separation.

Inferred read-only

generate_ui_pack

Get a cost preview for an exact component list and batch breakdown, then generate using the returned signed quote.

Inferred read-only

revise_ui_pack_png

Get a cost preview for a 100-credit selected PNG revision, then pass its signed quote to execute.

Potential side effects

rename_ui_component

Rename an owned component for free.

Inferred read-only

save_ui_component_defaults

Save supported fill, text and layout values for an exact current revision.

Inferred read-only

replace_ui_component_png

Save a locally edited PNG, revalidate behavior metadata and preserve the prior revision.

Inferred read-only

create_ui_composition

Create a free static composition of existing icon/frame revisions; indicators and functional widgets remain independent.

Potential side effects

get_ui_pack_export_command

Return an authenticated curl command for a whole/selected UI Pack ZIP or component source.

Potential side effects

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.spriteship]
url = "https://spriteship.com/mcp"
enabled = true

Claude Code

.mcp.json

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

Claude Desktop

Settings → Connectors → Add custom connector

Name: spriteship
Remote MCP URL: https://spriteship.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "spriteship": {
      "url": "https://spriteship.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "spriteship": {
      "type": "http",
      "url": "https://spriteship.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "spriteship",
  "transport": "streamable-http",
  "url": "https://spriteship.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.