Install
$ agentstack add mcp-abidoo22-pixelorama-mcp ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
🎨 pix-MCP
> For the ones who can imagine it but can't draw it.
pix-MCP is a Model Context Protocol (MCP) server that bridges AI assistants (Claude, GPT, Gemini, etc.) with Pixelorama, the free & open-source pixel art editor.
You describe what you want. The AI handles the rest — shapes, colours, shading, layers, animations, and full sprites — drawn live inside Pixelorama.
✨ Two Ways to Create
🤖 Way 1 — Describe it, AI draws it
Connect to Claude or any MCP client and describe your sprite in plain English: > "Draw a golden coin with a 3D star and drop shadow on a 64x64 canvas"
The AI computes the geometry, shading, and outlines, then draws it pixel by pixel inside Pixelorama.
🖼️ Way 2 — Import any image as pixel art
Already have a reference image (AI-generated or hand-drawn)? Import it directly:
node docs/examples/import_universal_asset.js
The importer auto-detects the background, strips it out, and streams the pixel-perfect asset into Pixelorama with full transparency.
🗂️ Where to Start
| You want to… | Go here | |---|---| | Install & connect to Claude/Cursor | [Getting Started Guide](docs/getting-started.md) | | Run a JS drawing script manually | [Custom Scripts Guide](docs/getting-started.md#manual-scripts) | | Import an existing image into Pixelorama | [Image Import Guide](docs/getting-started.md#image-import) | | See all available tools | [Tool Reference](docs/tool-reference.md) | | Build or fix the Pixelorama plugin | [Plugin Setup](docs/plugin-setup.md) | | Write an AI agent that draws | [Agentic Drawing Playbook](AGENTICDRAWINGPLAYBOOK.md) | | See worked examples | [docs/examples/](docs/examples/) |
🏗️ Architecture
AI Client (Claude / Cursor / any MCP client)
│ MCP — JSON-RPC over stdio
▼
pix-MCP Server (TypeScript / Node.js)
│ HTTP REST — localhost:7373
▼
Pixelorama Bridge Plugin (GDScript)
│ ExtensionsApi v8
▼
Pixelorama v1.1.10
⚡ Quick Start
Prerequisites
- Node.js ≥ 18
- Pixelorama v1.1.10
1. Install the MCP server
git clone https://github.com/abidoo22/Pixelorama-MCP.git
cd Pixelorama-MCP/mcp-server
npm install && npm run build
2. Install the Pixelorama plugin
- Open Pixelorama → Edit → Preferences → Extensions
- Click Add Extension and select
pixelorama-plugin/PixMcpBridge.pck - Enable it and restart Pixelorama
3. Connect Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"pix-mcp": {
"command": "node",
"args": ["/absolute/path/to/pix-MCP/mcp-server/dist/index.js"]
}
}
}
Then ask Claude: "Create a 64×64 canvas and draw a shiny red apple with a drop shadow"
🎮 Example Gallery
| Sprite | Method | Script | |---|---|---| | 🪙 Golden Coin | Drawn by AI agent | docs/examples/draw_coin.js | | 🥔 Potato | Drawn by AI agent | docs/examples/draw_potato.js | | 🍌 Banana | Drawn by AI agent | docs/examples/draw_banana.js | | 🌲 Tree | Drawn by AI agent | docs/examples/draw_tree.js | | 💪 Muscular Man | Imported from AI image | docs/examples/import_universal_asset.js | | Any image | Imported from AI image | docs/examples/import_universal_asset.js |
📖 Documentation
- [Getting Started](docs/getting-started.md) — Setup, prerequisites, client integration, and image import
- [Tool Reference](docs/tool-reference.md) — All 35+ MCP tools with parameters and return formats
- [Plugin Setup](docs/plugin-setup.md) — Compiling the GDScript plugin, troubleshooting quarantine
- [Agentic Drawing Playbook](AGENTICDRAWINGPLAYBOOK.md) — Shading math, geometry recipes, and batch optimization for AI agents
🛠️ Development
cd mcp-server
npm install
npm run dev # watch mode
# Test with MCP Inspector
npx @modelcontextprotocol/inspector node dist/index.js
🤝 Contributing
Contributions are welcome! Please read [CONTRIBUTING.md](CONTRIBUTING.md) before submitting a PR.
📄 License
[MIT](LICENSE) — go wild.
🙏 Credits
- Pixelorama by Orama Interactive
- Model Context Protocol by Anthropic
Source & license
This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: abidoo22
- Source: abidoo22/Pixelorama-MCP
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.