VibeGen

io.github.marstudio360v1.0.0更新于 Oct 6, 2026

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

已验证STDIO仅桌面Developer Tools Media & Design

概览

AI 生成的概览

将 AI 助手连接到正在运行的 VibeGen 生成艺术工作室，使其能读取画布、调整参数、切换引擎并保存预设。

功能: VibeGen MCP 通过工作室的 HTTP API 与实时运行的 VibeGen 工作室通信。助手可以读取当前引擎、参数值、结构和已应用的配方，进行部分参数更新、切换引擎，并短暂高亮它正在讨论的滑块。它还能列出、读取、写入和应用预设 JSON 文件，截取画布的 PNG 快照，以及读取或替换引擎的 GLSL 或 TypeScript 源码，替换后会热重载到画布中。
适用场景: 当你已经运行或使用 VibeGen 生成艺术工作室，并希望助手检查和控制实时画布、调节参数、管理预设，或在浏览器中观察效果的同时编辑引擎源码时，适合使用。
运行要求: 本地 Python 3.11+ 运行环境及该服务器的 Python 依赖。需要一个可访问的 VibeGen 工作室，可以是自己的实例或托管版本，通过 STUDIO_URL 设置（默认 STUDIO_TOKEN 提供并以 x-studio-token 请求头发送。仅限桌面端；画面在浏览器中使用你自己的 GPU 渲染。

安装前请注意

STUDIO_TOKEN 是共享密钥，仅当你的工作室服务器启用了 STUDIO_API_TOKEN 时才应设置。该服务器可以写入预设文件并替换引擎源码，替换后会热重载到实时画布，因此更改会立即生效。所有调用只发往 STUDIO_URL，不会发往其他地方，因此请只指向你信任的工作室。

安装

在 SourceWeft 中

打开控制台中的 VibeGen，将其添加到工作区。
为需要使用其工具的对话启用该服务。

Desktop only，通过 STDIO。 STDIO 服务会启动本地进程，因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照仓库中的启动说明。

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]

来源：README.md，提交 ee4b975

工具

工具元数据尚未被收录。

版本历史

v1.0.0最新Oct 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