SpriteShip
SpriteShip for Cline

AI game art for Cline

Cline reads .clinerules, runs in your editor with your terminal, and asks before acting — which lines up exactly with how paid generation is designed to work.

Connect

Point Cline at the MCP server.

40 tools over one endpoint — list, read, export, curate frames, generate. Same key, same guardrails as the REST API, and paid tools preview their cost before they run.

Add to your MCP config
{
  "mcpServers": {
    "spriteship": {
      "url": "https://spriteship.com/mcp",
      "headers": {
        "Authorization": "Bearer ${env:SPRITESHIP_API_KEY}"
      }
    }
  }
}

Cline manages MCP servers from its MCP Servers panel, which writes this same JSON. Add it there rather than by hand if you prefer — the entry is identical.

Key + smoke test
# 1. Point your agent's shell at your key
export SPRITESHIP_API_KEY="ss_live_..."

# 2. Confirm it works
curl -sS -H "Authorization: Bearer $SPRITESHIP_API_KEY" \
  https://spriteship.com/api/v1/me

# 3. Teach the agent the API — the skill ships an AGENTS.md
cat <spriteship-skill>/AGENTS.md >> AGENTS.md
Optional, and worth it

Add the skill too.

MCP gives Cline the tools. The skill gives it the recipes — how to sync into a project tree, how to re-sync only what changed, and the protocol it must follow before spending a credit. They compose.

Add the rule
# The skill ships an AGENTS.md — drop it in as a rules file:
mkdir -p .clinerules
cp <spriteship-skill>/AGENTS.md .clinerules/spriteship.md

# Already have Cursor/Windsurf rules? Same content works:
#   cp .cursor/rules/spriteship.mdc .clinerules/spriteship.md

Cline uses the .clinerules directory as its primary rules format, and also reads AGENTS.md. If you already keep Cursor or Windsurf rules, the same file content works — copy it across. <spriteship-skill> is the SpriteShip agent skill — getting the skill →

Why it fits

Built for how Cline works.

Approval-first matches spend-first

Cline shows you each command before it runs. Paired with the dry-run cost preview, you see both what will happen and what it costs before a single credit moves.

It runs curl, so there is nothing to install

The whole integration is HTTP with a bearer token. No server, no extension, no dependency to keep current — the rules file only tells Cline which endpoints exist.

Plan mode reads the schema first

Because every export bundle carries its own JSON Schema and manifest, Cline can plan the wiring from the actual file inventory instead of assuming a layout.

Worked example

One ask, start to finish.

"the goblin's attack animation has too many frames — trim it to the good ones"

  1. 01Fetches the animation’s frames as presigned thumbnails or one contact sheet
  2. 02Looks at them and proposes which indices to keep
  3. 03Calls select-frames with the ordered list — free, no regeneration
  4. 04Re-syncs the rebuilt sheet and atlas into your project
The actual loop

The full loop, once.

Every agent runs the same shape — resolve, preview the cost, confirm, generate, poll, write the files, wire the code.

Session
you › the knight needs a dodge-roll animation, then wire it into the player state machine

  agent › GET /api/v1/characters?name=knight
          → chr_8fq2… · contentVersion 4a1c… · 6 animations

  agent › POST /api/v1/characters/chr_8fq2…/generate-pose  { dryRun: true }
          → 400 credits · balance 1,500 → 1,100

  you   › go ahead

  agent › POST /api/v1/characters/chr_8fq2…/generate-pose
          Idempotency-Key: 7c1f-…
          → job_2b9e… queued
  agent › GET /api/v1/jobs/job_2b9e…            → running
  agent › GET /api/v1/jobs/job_2b9e…            → done · 400 credits charged

  agent › GET /api/v1/characters/chr_8fq2…/export?engine=phaser&format=json
          → wrote assets/spriteship/knight/spritesheet.png
            wrote assets/spriteship/knight/atlas.json
            wrote spriteship.lock.json  (contentVersion 91be…)

  agent › edited src/player/PlayerStateMachine.ts
          + case 'dodge': this.play('dodge_roll'); break;

done — dodge_roll is registered and playable. 400 credits spent.
Guardrails

Handing an agent a budget, safely.

An agent that can spend money needs more than an API key. Every one of these is enforced server-side — not a convention the agent is trusted to follow.

Scoped keys

Four scopes, granted separately: assets:read, account:read, assets:write, credits:spend. A read-only key physically cannot spend money.

Per-key spend caps

Every key carries a daily credit ceiling — 5,000 by default, 50,000 maximum. Accounting is gross, so refunds restore your balance but never hand the key back headroom.

Over MCP, paid tools preview by default

Every paid MCP tool defaults to a dry run: it returns the exact credit cost and your resulting balance, and executes nothing. The agent has to deliberately re-call with dryRun:false to spend. Accidental spend is not a thing it can stumble into.

Idempotency keys

Paid writes require an Idempotency-Key header. A retried request replays the original job pointer instead of starting — and paying for — a second generation.

Busy-entity guard

A write against an entity that already has a job running answers ENTITY_BUSY rather than racing it, so two agents (or one confused agent) cannot corrupt the same character.

Re-sync signals

Every read carries contentVersion or updatedAt. The agent diffs those against its lock file and re-downloads only what actually changed after you edited something in the dashboard.

Presigned binaries

Every sheet, atlas, zip and preview URL is presigned and expiring. Nothing in an API response is a permanent public link.

Kill switch

Revoking a key cancels its in-flight jobs and refunds their unfinished charges. Leaked keys found by GitHub secret scanning are revoked automatically and you get an email.

What lands in your repo

Output an agent can actually use.

A folder of PNGs makes an agent guess. Every SpriteShip export explains itself, so the agent wires it up instead of improvising.

Self-describing bundles

Every export zip carries a manifest (tizo-export.json), a JSON Schema of its own shape, a README, a runnable preview and a SKILL.md — so an agent can consume the output without you explaining the format.

Native engine files

Phaser atlases, Godot 4 .tres resources, Unity sliced sprites with stable GUIDs, GameMaker sprite strips and Tiled tilesets. Not a folder of PNGs the agent has to guess at.

Collision, not bounding boxes

Authored collision bodies and ground footprints ride through the API and into every export, so the agent builds the real collider instead of defaulting to the sprite rectangle.

Mount points

Per-frame anchor points for weapons, hands and heads travel with the animation, so the agent can parent a projectile spawn to the right pixel on the right frame.

Questions

Cline, specifically.

Can it curate frames without spending credits?

Yes. Frame inspection and select-frames need only the assets:write scope, not credits:spend. Re-curating an existing animation rebuilds from cached frames — no AI call, no charge.

What happens if I stop it mid-generation?

Cancel the job through the API or the dashboard and any unfinished charge is refunded. Revoking the key does the same for everything that key has in flight.

Point Cline
at your art.

1,500 free credits, no card. Reading and re-syncing never cost anything.

Start free — 1,500 credits