mcpField
S
SpriteCook

SpriteCook

Remote
github.com/spritecookMedia & Design6Updated 10w ago
Repository

About SpriteCook

SpriteCook’s MCP server connects AI agents to its service for generating pixel art and game assets. Setup can detect supported clients, configure connections, and optionally install an agent skill.

Key features

  1. 01Generate pixel art and game assets
  2. 02Create sprite sheets and animations
  3. 03Use saved character presets
  4. 04Upload local files and remove backgrounds
  5. 05Organize and rename generated assets

Use cases

  1. 01Create sprites and tilesets for a 2D game
  2. 02Generate icons with transparent backgrounds
  3. 03Animate an uploaded character image

MCP support

Exposes SpriteCook asset-generation capabilities to MCP clients through its hosted MCP endpoint. The setup command can configure client connections; authentication uses an API key where required, while Grok Build uses host-managed OAuth.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://api.spritecook.ai/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

All endpoints
Streamable HTTPhttps://api.spritecook.ai/mcpAuth required

Tools

Details

From the project README

spritecook-mcp

Connect your AI agent (Cursor, VS Code, Claude, Codex, Grok Build, and others) to SpriteCook for AI-powered pixel art and game asset generation.

Quick Setup

npx spritecook-mcp setup

This will:

  1. Detect your installed AI clients, including Grok Build
  2. Authenticate with an API key where required; Grok Build uses host-managed OAuth
  3. Configure MCP connections automatically
  4. Install an optional agent skill for smarter AI integration

The optional skills include current guidance for asynchronous job polling, canonical sprite_url output, model discovery, GPT-Image-2 quality settings, guided character workflows, saved presets, multi-image style guide references, local-file uploads, background cleanup, asset organization and recovery, and Godot-ready character exports.

What You Get

After setup, your AI agent can generate pixel art and game assets directly:

"Generate a 64x64 pixel art sword sprite"

"Create a character sprite sheet for my platformer game"

"Make a set of potion icons with transparent backgrounds"

"Use my character preset for a new idle sprite"

"Import this local boss PNG, then animate it with a slow idle motion"

"Remove the background from this character asset and give me the transparent PNG"

"Rename the generated sword asset to Iron Sword Pickup"

Manual Configuration

If you prefer to configure manually, add this to your editor's MCP config:

Cursor (.cursor/mcp.json):

{
  "mcpServers": {
    "spritecook": {
      "url": "https://api.spritecook.ai/mcp/",
      "headers": { "Authorization": "Bearer YOUR_API_KEY" }
    }
  }
}

VS Code (.vscode/settings.json):

{
  "mcp": {
    "servers": {
      "spritecook": {
        "type": "http",
        "url": "https://api.spritecook.ai/mcp/",
        "headers": { "Authorization": "Bearer YOUR_API_KEY" }
      }
    }
  }
}

Grok Build (.grok/config.toml or ~/.grok/config.toml):

[mcp_servers.spritecook]
url = "https://api.spritecook.ai/mcp/oauth"
enabled = true
tool_timeout_sec = 6000

Open /mcps in Grok Build and authenticate spritecook. Grok stores and refreshes OAuth credentials without exposing them to the model. If tools do not appear, run grok mcp doctor spritecook and grok inspect.

The repository also includes a root .mcp.json for a Grok Build marketplace submission. Publishing the marketplace listing is a separate release step.

Environment Variables

  • SPRITECOOK_API_URL - Override the API base URL (for local development)

Links

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.