Studio — Claude Code MCP server: visual workflows from your agent
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.
claude mcp add --transport http studio https://mcp.studio.kaitoi.ioWhat studio 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.
What it helps with
- 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 for the agent
- 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
How to install studio
Platform CLI: remote server
claude mcp add --transport http studio https://mcp.studio.kaitoi.ioPlatform CLI: remote server
codex mcp add studio --url https://mcp.studio.kaitoi.ioConfig file
{
"mcpServers": {
"studio": {
"url": "https://mcp.studio.kaitoi.io"
}
}
}Config file
{
"servers": {
"studio": {
"type": "http",
"url": "https://mcp.studio.kaitoi.io"
}
}
}Platform CLI: remote server
gemini mcp add -t http studio https://mcp.studio.kaitoi.ioStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about studio
How do I install Studio in Claude Code?
Run claude mcp add --transport http studio https://mcp.studio.kaitoi.io. First, open Kaitoi Studio (Settings → MCP), generate an API token for your client, and add it to your MCP configuration per your client's docs.
What does Studio do?
It's an MCP server that lets your AI agent load, edit, and run creative workflows. Your agent can add nodes (video processors, models, filters), tweak parameters, validate the graph, and execute it. Graphs mix providers: Fal.ai, OpenAI, Stability, Replicate, and more.
Which platforms does Studio support?
Any MCP client with HTTP and Bearer token auth: Claude Code, Codex, Cursor, GitHub Copilot, Windsurf, Cline, Zed, and Gemini CLI.
