VibeGen

io.github.marstudio360v1.0.0Updated Oct 6, 2026

Lets your AI drive a live generative art studio: read the canvas, move knobs, switch engines.

VerifiedSTDIODesktop onlyDeveloper Tools Media & Design

Overview

AI-generated overview

Connects an AI assistant to a running VibeGen generative art studio so it can read the canvas, adjust parameters, switch engines, and save presets.

What it does: VibeGen MCP talks to a live VibeGen studio over its HTTP API. The assistant can read the current engine, parameter values, schema and applied recipe, apply partial parameter updates, switch engines, and briefly highlight the sliders it is discussing. It can list, read, write and apply preset JSON files, capture a PNG snapshot of the canvas, and read or replace an engine's GLSL or TypeScript source, which hot-reloads into the canvas.
When to use it: Use it when you already run or use a VibeGen generative art studio and want an assistant to inspect and steer the live canvas, tune parameters, manage presets, or edit engine source while you watch the result in the browser.
Requirements: A local Python 3.11+ runtime and the server's Python dependencies. A reachable VibeGen studio, either your own instance or the hosted one, set via STUDIO_URL (default Writing engine source needs a studio tier that accepts a token, supplied as STUDIO_TOKEN and sent in the x-studio-token header. Desktop only; the art renders in the browser on your own GPU.

Before you install

STUDIO_TOKEN is a shared secret and should only be set if your studio server enforces STUDIO_API_TOKEN. The server can write preset files and replace engine source, which hot-reloads into the live canvas, so changes take effect immediately. All calls go to STUDIO_URL and nowhere else, so point it only at a studio you trust.

Installation

In SourceWeft

Open VibeGen in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

VibeGen MCP

Lets your AI drive a live generative art studio: read the canvas, move knobs, switch engines.

VibeGen MCP connects your AI to a running VibeGen generative art studio over the studio's HTTP API. It reads the live canvas state and every parameter, moves sliders and switches engines in real time, briefly highlights the controls it is talking about, saves, lists, reads and applies presets as JSON files, and captures a PNG snapshot of the canvas so the AI can see what it made. It can also read an engine's source (GLSL or TypeScript) and write a new version that hot-reloads into the canvas.

Point it at the hosted studio (reached through vibedna.ai/studio) or at your own instance. The art renders in the browser, on your own GPU. What the studio allows depends on your studio tier: writing engine source needs a token that the studio accepts.

Homepage: https://vibedna.ai/store/vibegen

Tools (12)

Tool	What it does
`get_state()`	Engine id, every parameter value, schema, applied recipe
`set_params(params)`	Partial parameter update, applied live
`set_engine(engine_id)`	Switch engine
`highlight_params(keys)`	Briefly flash specific sliders
`list_saves()`	List preset JSON files in the studio's saves folder
`read_save(rel_path)`	Read one preset
`write_save(rel_path, content)`	Write a preset
`apply_save(rel_path)`	Load a preset into the live studio
`read_engine_source(engine_id)`	Read an engine's source
`write_engine_source(engine_id, code)`	Replace an engine's source; the studio hot-reloads it
`snapshot_canvas(save_to, timeout_seconds)`	PNG capture of the live canvas
`vibedna_info()`	What this MCP does and which studio it points at

Install

bash

git clone https://github.com/marstudio360/vibegen-mcpcd vibegen-mcppip install -r requirements.txt

git clone https://github.com/marstudio360/vibegen-mcpcd vibegen-mcppip install -r requirements.txt

Python 3.11+.

Claude Code

bash

claude mcp add vibegen --scope user -e STUDIO_URL=http://localhost:3000 -- python /absolute/path/to/vibegen-mcp/server.py

claude mcp add vibegen --scope user -e STUDIO_URL=http://localhost:3000 -- python /absolute/path/to/vibegen-mcp/server.py

Or in a project's .mcp.json:

json

{  "mcpServers": {    "vibegen": {      "command": "python",      "args": ["/absolute/path/to/vibegen-mcp/server.py"],      "env": {        "STUDIO_URL": "http://localhost:3000",        "STUDIO_TOKEN": ""      }    }  }}

{  "mcpServers": {    "vibegen": {      "command": "python",      "args": ["/absolute/path/to/vibegen-mcp/server.py"],      "env": {        "STUDIO_URL": "http://localhost:3000",        "STUDIO_TOKEN": ""      }    }  }}

Cursor

Add the same mcpServers block to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (one project).

Claude Desktop

Add the same mcpServers block to claude_desktop_config.json (Settings > Developer > Edit Config), then restart Claude Desktop.

The shortest path for the hosted studio: open vibedna.ai/studio, click Set up in your AI, and drop the file it gives you into your AI chat. INSTALL.md covers the manual path step by step.

Configuration

To watch the changes live, open the studio with ?remote=1 (for example http://localhost:3000/?remote=1).

Network

Every call goes to STUDIO_URL and nowhere else.

License

Support: [email protected]

Source: README.md at commit ee4b975

Tools

Tool metadata has not been indexed yet.

Version history

v1.0.0LatestOct 6, 2026

Variable	Default	What it does
`STUDIO_URL`	`http://localhost:3000`	The studio API host to drive
`STUDIO_TOKEN`	(empty)	Sent as `x-studio-token`; needed only when the studio enforces one