> ## Documentation Index
> Fetch the complete documentation index at: https://docs.xhuoapi.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Seedance MCP Integration Guide

> seedance MCP 服务器集成

[MCP (Model Context Protocol)](https://modelcontextprotocol.io) is a model context protocol launched by Anthropic that allows AI models (such as Claude, GPT, etc.) to call external tools through standardized interfaces. With the Seedance MCP Server provided by XHuoAPI, you can directly use ByteDance Seedance to generate AI videos within AI clients like Claude Desktop, VS Code, Cursor, and more.

## Feature Overview

Seedance MCP Server offers the following core features:

* **Text-to-Video Generation** — Generate high-quality videos from text prompts
* **Image-to-Video Generation** — Generate videos using images as references (first frame, last frame, reference image modes)
* **Multi-Model Support** — Supports various models including Seedance 1.5 Pro, 1.0 Pro, 1.0 Lite, etc.
* **Multiple Resolutions** — Supports 480p, 720p, 1080p resolutions
* **Various Aspect Ratios** — Supports 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, and other ratios
* **Flexible Duration** — Supports video lengths from 2 to 12 seconds
* **Audio Generation** — Some models support simultaneous audio generation
* **Task Querying** — Monitor generation progress and retrieve results

## Prerequisites

Before use, you need to obtain an XHuoAPI API Token:

1. Register or log in at [XHuoAPI Platform](https://api.xhuoapi.ai)
2. Navigate to the [Seedance Videos API](https://api.xhuoapi.ai/documents/seedance-videos) page
3. Click "Acquire" to get your API Token (first-time applicants receive free quota)

## Installation and Configuration

### Method 1: pip Installation (Recommended)

```bash theme={null}
pip install mcp-seedance
```

### Method 2: Source Installation

```bash theme={null}
git clone https://github.com/XHuoAPI/SeedanceMCP.git
cd SeedanceMCP
pip install -e .
```

After installation, you can start the service using the `mcp-seedance` command.

## Using in Claude Desktop

Edit the Claude Desktop configuration file:

* **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`
* **Windows**: `%APPDATA%\Claude\claude_desktop_config.json`

Add the following configuration:

```json theme={null}
{
  "mcpServers": {
    "seedance": {
      "command": "mcp-seedance",
      "env": {
        "XHuoAPI_API_TOKEN": "your API Token"
      }
    }
  }
}
```

If using `uvx` (no need to pre-install packages):

```json theme={null}
{
  "mcpServers": {
    "seedance": {
      "command": "uvx",
      "args": ["mcp-seedance"],
      "env": {
        "XHuoAPI_API_TOKEN": "your API Token"
      }
    }
  }
}
```

Save the configuration and restart Claude Desktop. You can then use Seedance-related tools in conversations.

## Using in VS Code / Cursor

Create `.vscode/mcp.json` in the project root directory:

```json theme={null}
{
  "servers": {
    "seedance": {
      "command": "mcp-seedance",
      "env": {
        "XHuoAPI_API_TOKEN": "your API Token"
      }
    }
  }
}
```

Or use `uvx`:

```json theme={null}
{
  "servers": {
    "seedance": {
      "command": "uvx",
      "args": ["mcp-seedance"],
      "env": {
        "XHuoAPI_API_TOKEN": "your API Token"
      }
    }
  }
}
```

## Available Tools List

| Tool Name                            | Description                                      |
| ------------------------------------ | ------------------------------------------------ |
| `seedance_generate_video`            | Generate video from text prompt                  |
| `seedance_generate_video_from_image` | Generate video using image as reference          |
| `seedance_get_task`                  | Query single task status                         |
| `seedance_get_tasks_batch`           | Batch query task statuses                        |
| `seedance_list_models`               | List all available models and their capabilities |
| `seedance_list_resolutions`          | List available resolutions and aspect ratios     |
| `seedance_list_actions`              | List all available tools and workflow examples   |

## Usage Examples

After configuration, you can directly invoke these features in AI clients using natural language, for example:

* "Help me generate a city street time-lapse video using Seedance"
* "Use this photo as the first frame to generate an 8-second video"
* "Generate a 1080p vertical 9:16 short video"
* "Generate a video with audio using the Seedance 1.5 Pro model"

## More Information

* GitHub Repository: [XHuoAPI/SeedanceMCP](https://github.com/XHuoAPI/SeedanceMCP)
* PyPI Package: [mcp-seedance](https://pypi.org/project/mcp-seedance/)
* API Documentation: [Seedance Video Generation API](https://api.xhuoapi.ai/documents/seedance)