# studio

Connect your agent to Kaitoi Studio and orchestrate creative production pipelines from chat. Add nodes, wire them together, run the graph—all through Claude, Cursor, or another MCP client.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: kaitoi-labs
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/kaitoi-labs/kaitoi-mcp
- Updated: 2026-04-18
- HTML: https://affpapa.org/en/nevibecode/mcp/studio

## What it does

Studio exposes Kaitoi Studio's workflow engine to AI agents via MCP. You design pipelines in the visual editor; your agent can load projects, search and add nodes from the library, modify parameters, and execute the graph or individual nodes. Both you and the agent work in the same workspace.

The server supports node discovery by name and function, wires together providers (Fal.ai, OpenAI, Stability, Replicate, ElevenLabs, and others), validates graphs before execution, and persists results. Tools let you manage nodes and connections, read and edit custom node scripts, fetch Fal API documentation, and perform web search and crawl. Workflows are saved and reused across projects, not discarded after one generation.

Studio is in private beta; you need an account and API token generated in the app (Settings → MCP). Configure your MCP client with the token and endpoint `https://mcp.studio.kaitoi.io`. After setup, ask your agent to list your projects to verify the connection.

## Requirements
- Remote server: `https://mcp.studio.kaitoi.io`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http studio https://mcp.studio.kaitoi.io
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add studio --url https://mcp.studio.kaitoi.io
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "studio": {
            "url": "https://mcp.studio.kaitoi.io"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "studio": {
            "type": "http",
            "url": "https://mcp.studio.kaitoi.io"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http studio https://mcp.studio.kaitoi.io
```

## When to use it
- orchestrate color grading, video synthesis, and audio pipelines without leaving chat
- discover and wire AI models from multiple providers into one workflow
- compose graphs for image, video, 3D, audio and document generation
- catch graph errors before rendering
- build reusable production systems instead of one-shot prompts

## Example prompts
- Find a fast image-to-video model with lip-sync on Fal, wire it to the CastingShot node in my graph, and run a test render
- Write a custom node that applies LUTs from my library to image batches, validate it against the spec, then drop it after ImageBatch

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 392262
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33989
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81163
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119231
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47577
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43902

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md