Skip to content
MCP server

TaoDock AI Image & Video

Local MCP server that generates images and videos through your Taodock account

Runs locallyStatus and history
Install
Platforms
macOS, Windows, Linux
Runs
Locally
Version
0.2.0
Listing updated
today

Similar MCP servers

About TaoDock AI Image & Video

TaoDock AI Image & Video is an MCP server for design and media. It runs locally on your machine and is started by your AI client.

Taodock is described on its site as a unified API gateway for AI models, and this server brings its image and video models into MCP clients. One API key finds the models authorised for your account, generates images, starts asynchronous video jobs, checks their status and downloads finished media.

It runs locally over stdio from the npm package @taodock-ai/mcp-server and does not expose a remote HTTP or SSE endpoint. Generated files are written to a folder on your computer, set with TAODOCK_OUTPUT_DIR. Generation consumes Taodock quota, so a funded account is needed.

The README gives setup for Claude Desktop (including a signed .mcpb release), Cursor, LobeHub Desktop, VS Code and Gemini CLI. It requires Node.js 20.11 or later, and error messages can be switched between English and Chinese with TAODOCK_LOCALE.

Install

Run in a terminal

claude mcp add mcp-server --env TAODOCK_API_KEY='<TAODOCK_API_KEY>' -- npx -y @taodock-ai/mcp-server

Add to claude_desktop_config.json

{
  "mcpServers": {
    "mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@taodock-ai/mcp-server"
      ],
      "env": {
        "TAODOCK_API_KEY": "<TAODOCK_API_KEY>"
      }
    }
  }
}

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@taodock-ai/mcp-server"
      ],
      "env": {
        "TAODOCK_API_KEY": "<TAODOCK_API_KEY>"
      }
    }
  }
}

Add to .vscode/mcp.json

{
  "servers": {
    "mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@taodock-ai/mcp-server"
      ],
      "env": {
        "TAODOCK_API_KEY": "<TAODOCK_API_KEY>"
      }
    }
  }
}

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

{
  "mcpServers": {
    "mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@taodock-ai/mcp-server"
      ],
      "env": {
        "TAODOCK_API_KEY": "<TAODOCK_API_KEY>"
      }
    }
  }
}

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

{
  "mcpServers": {
    "mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@taodock-ai/mcp-server"
      ],
      "env": {
        "TAODOCK_API_KEY": "<TAODOCK_API_KEY>"
      }
    }
  }
}

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

Configuration

  • TAODOCK_API_KEYTaoDock API key from https://taodock.com/keysRequired
  • TAODOCK_BASE_URLOptional HTTPS API base URL override; defaults to https://taodock.com/v1. The API key is sent to this endpoint.
  • TAODOCK_OUTPUT_DIRDirectory for generated files; an absolute path is recommended
  • TAODOCK_LOCALEError message language: en or zh

What it does

Model discovery
Lists the image and video models your API key is authorised for.
Image generation
Creates images from an MCP client.
Async video jobs
Starts video generation and checks job status later.
Media download
Saves completed files to a local output directory.
Pinned install
Run a fixed npm version for reproducible client startup.
English or Chinese errors
TAODOCK_LOCALE selects the error language.

Good for

  • Generate images from inside Cursor or Claude Desktop
  • Start a video render and poll until it finishes
  • See which models your account may use
  • Save generated media into a project folder

Pricing

Pricing unknown

Uses Taodock account quota; prices not published here

Prices change. Check taodock.com before you buy.

TaoDock AI Image & Video FAQ

What do I need to use it?

Node.js 20.11 or later, a Taodock account and API key, and an MCP client that can launch a local stdio server.

Is there a remote endpoint?

No. The README says it uses local stdio only.

Does generation cost anything?

Image and video generation consume Taodock quota; the pricing is not given in the README.

Which clients are documented?

Claude Desktop, Cursor, LobeHub Desktop, VS Code and Gemini CLI.

How do I add TaoDock AI Image & Video to Claude Code?

Run this command in your terminal: claude mcp add mcp-server --env TAODOCK_API_KEY='<TAODOCK_API_KEY>' -- npx -y @taodock-ai/mcp-server

What are the best alternatives to TaoDock AI Image & Video?

The closest alternatives to TaoDock AI Image & Video are HyperFrames by HeyGen, headroom, omniget, next-ai-draw-io and mcp-for-blender.

Where this comes from

  • Description: written from the project's README and the project's website.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers