genart-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@genart-mcpCreate a p5.js sketch with rotating squares"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@genart-dev/mcp-server
Model Context Protocol server for genart.dev — 33 tools, 4 resources, and 3 prompts for creating and manipulating generative art with AI agents.
Works with any MCP client: Claude Code, Claude Desktop, Codex CLI, Cursor, and more.
Install
npm install -g @genart-dev/mcp-serverFor screenshot/export capture, also install Puppeteer:
npm install -g puppeteerQuick Start
Claude Code
claude mcp add genart-mcp -- genart-mcpClaude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"genart": {
"command": "genart-mcp"
}
}
}Codex CLI
Add to .codex/config.toml:
[mcp_servers.genart]
command = "genart-mcp"Then ask your AI agent to create generative art:
"Create a workspace with a p5.js sketch that draws a grid of rotating squares using the golden ratio"
Tools (33)
Workspace (5)
Tool | Description |
| Create a new |
| Open an existing |
| Add an existing |
| Remove a sketch from workspace (optionally delete file) |
| List all sketches with metadata summaries |
Sketch Lifecycle (7)
Tool | Description |
| Create a new |
| Open a sketch by ID and set selection |
| Update metadata, parameters, colors, canvas |
| Replace algorithm source code with optional validation |
| Persist in-memory state to disk |
| Create a variant with new ID and optional modifications |
| Delete sketch file and remove from workspace |
Selection & Context (4)
Tool | Description |
| Full context for selected sketch(es) — algorithm, params, colors, philosophy |
| Set canvas selection to one or more sketches |
| Full snapshot of workspace, sketches, and selection |
| Set base directory for sandboxed file operations |
Parameters (5)
Tool | Description |
| Update runtime parameter values |
| Update runtime color palette values |
| Set random seed (or generate random) |
| Change dimensions via preset or explicit W/H |
| Generate random values for all/specific parameters |
Arrangement (3)
Tool | Description |
| Move sketches to explicit canvas positions |
| Auto-layout with grid, row, column, or masonry |
| Create/update named groups of sketches |
Gallery (2)
Tool | Description |
| Scan a directory for |
| Search loaded sketches by title, renderer, params, skills |
Merge (1)
Tool | Description |
| Combine parameters, colors, and philosophies from 2+ sketches |
Capture (3)
Tool | Description |
| Headless capture of a sketch — returns metadata + inline JPEG for AI viewing |
| Capture multiple sketches in parallel |
| Structural summary of workspace layout for spatial reasoning |
Export (1)
Tool | Description |
| Export as standalone HTML, PNG, SVG, raw algorithm, or ZIP bundle |
Knowledge (3)
Tool | Description |
| List available design knowledge skills by category |
| Load a skill with full theory, principles, and examples |
| Design guidelines for composition, color, parameters, animation, performance |
Resources (4)
URI | Description |
| Available design knowledge skills |
| Canvas dimension presets (18 built-in) |
| Loaded sketches with metadata summaries |
| Available renderer types and metadata |
Prompts (3)
Prompt | Description |
| Guided workflow: concept → sketch → algorithm → capture → iterate |
| Fork and explore parameter/seed space across multiple variants |
| Apply Gestalt, color theory, composition, rhythm, or contrast principles |
Supported Renderers
Type | Runtime | Algorithm |
| p5.js |
|
| Three.js |
|
| WebGL2 | Fragment shader source |
| Native |
|
| Native |
|
Library API
For programmatic use (e.g., building a custom MCP host):
import { createServer, EditorState } from "@genart-dev/mcp-server/lib";
const state = new EditorState();
const server = createServer(state);
// Connect to any MCP transport
// ...Exports from @genart-dev/mcp-server/lib
Export | Description |
| Create a configured |
| Server-scoped mutable state (workspace, sketches, selection) |
| Type — sketch definition + file path + dirty flag |
| Type — mutation event names ( |
| Type — mutation event payload |
| Type — serializable snapshot of all state |
EditorState
const state = new EditorState();
// Load from disk
await state.loadWorkspace("/path/to/project.genart-workspace");
// Access loaded sketches
state.sketches; // Map<string, LoadedSketch>
state.selection; // Set<string>
state.workspace; // WorkspaceDefinition | null
// Sandbox file operations (for hosted environments)
state.basePath = "/safe/dir";
state.remoteMode = true; // Return file content instead of writing to disk
// Listen for mutations
state.on("mutation", (event) => {
console.log(event.type); // "sketch:created", "workspace:loaded", etc.
});
// Serializable snapshot
const snapshot = state.getSnapshot();Modes
stdio (default)
Standard MCP transport for CLI agents:
genart-mcpSidecar
Stdio transport + IPC mutation bridge for Electron app integration:
genart-mcp --mode sidecarMutations are forwarded to the parent process via Node IPC, enabling real-time UI updates when AI agents modify sketches.
Agent Attribution
Most mutation tools accept optional agent and model parameters for provenance tracking:
{
"agent": "claude-code",
"model": "claude-opus-4-6"
}Stored in sketch metadata to track which AI agent created or modified each sketch.
Related Packages
Package | Purpose |
File format types, parsers, presets | |
Renderer adapters, skill registry (dependency) |
Support
Questions, bugs, or feedback — support@genart.dev or open an issue.
License
MIT
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/genart-dev/mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server