Skip to content
MCP server

shuut

Remote MCP server for generating and editing images, video, voice and captions from AI

Answers · sign-in required (OAuth)

The server answered an hour ago with a sign-in request for OAuth (HTTP 401), so we could not list its tools.

Install
Platforms
API, Web
Runs
Remotely
Access
Needs sign-in (OAuth)
Version
1.0.0
Listing updated
today

Similar MCP servers

About shuut

shuut is an MCP server for design and media. It runs as a hosted remote server, so there is nothing to install locally.

The shuut MCP endpoint lets AI assistants call image and video generation and editing features hosted by shuut. The MCP registry entry lists models including GPT Image, Seedance, Kling and Veo, covering image, video, voice and caption work.

The server is reached over streamable HTTP at the listed remote URL, so there is nothing to install locally. The vendor page says it connects with Claude, ChatGPT, Claude Code, Codex and Cursor, and that access is granted by signing in to a shuut account.

It suits people who already work in one of those assistants and want to produce media without leaving the chat. The page is in Korean, and the content provided does not describe pricing or a tool-by-tool list beyond the registry summary.

Install

Run in a terminal

claude mcp add --transport http shuut https://shuut.ai/mcp

Add to Settings → Connectors → Add custom connector

https://shuut.ai/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "shuut": {
      "url": "https://shuut.ai/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "shuut": {
      "type": "http",
      "url": "https://shuut.ai/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "shuut": {
      "serverUrl": "https://shuut.ai/mcp"
    }
  }
}

Add to Grok Bot desktop app → Connect apps → Add a custom connector

https://shuut.ai/mcp

Enter a Name (for example "shuut"), choose Type: Remote HTTPS, paste this as the Server URL and choose Add plugin. When we checked, this server asked for OAuth sign-in. If its docs give you an OAuth client ID and secret, enter them in the form's OAuth Client ID and Client Secret fields.

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "shuut": {
      "type": "http",
      "url": "https://shuut.ai/mcp"
    }
  }
}

Using several servers? Build one config file with the MCP config generator.

What it does

Remote streamable HTTP access
Connects to a hosted endpoint over streamable HTTP, so no local server needs to run.
Multiple generation models
The registry entry names GPT Image, Seedance, Kling and Veo as the underlying generation options.
Image and video creation
Generates and edits images and video from within a compatible AI client.
Voice and caption generation
The registry summary also lists voice and caption generation and editing.
Sign-in connection
Access is set up by logging in to a shuut account from the connection page.

Good for

  • Generating social media images or short videos from a chat assistant
  • Editing existing visuals by describing changes in natural language
  • Adding voiceovers or captions to clips while working in a coding or chat client

shuut FAQ

How do I connect to shuut's MCP server?

Use the remote URL https://shuut.ai/mcp over streamable HTTP and sign in to your shuut account, according to the connection page.

Which AI clients does it support?

The vendor page lists Claude, ChatGPT, Claude Code, Codex and Cursor.

Which generation models are available?

The MCP registry entry names GPT Image, Seedance, Kling and Veo.

How do I add shuut to Claude Code?

Run this command in your terminal: claude mcp add --transport http shuut https://shuut.ai/mcp

What are the best alternatives to shuut?

The closest alternatives to shuut are AI Image Editor MCP, Muse AI Image MCP, SocialSight, Affogato and FunAI Studio.

Where this comes from

  • Description: written from the project's website and its MCP Registry entry.
  • Status: checked automatically by AIPoweredBot on 19 November 2026.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers