Seedance MCP Integration Guide

MCP (Model Context Protocol) 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 辰汐ai, you can directly use ByteDance Seedance to generate AI videos in AI clients like Claude Desktop, VS Code, Cursor, etc.

Feature Overview

The Seedance MCP Server provides the following core functionalities:

  • Text to Video — Generate high-quality videos from text prompts
  • Image to Video — Generate videos based on images (first frame, last frame, reference image, etc.)
  • Multi-Model Support — Supports Seedance 1.x, 1.5, 2.0, and 2.5
  • Multiple Resolutions — Supports 480p, 720p, 1080p, with some models supporting 4k
  • Various Aspect Ratios — Supports 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, and adaptive
  • Flexible Duration — Supports 2–30 seconds or automatic duration based on the model
  • Multimodal Video — Supports audio generation, reference audio/video, and video editing and extension in 2.5
  • Task Query — Monitor generation progress and obtain results

Prerequisites

Before use, you need to obtain an 辰汐ai API Token:

  1. Register or log in to the 辰汐ai platform
  2. Go to the Seedance Videos API page
  3. Click "Acquire" to get the API Token (first-time applicants receive free credits)

Method 1: Use Hosted MCP Server (Recommended, Zero Installation)

辰汐ai has hosted the Seedance MCP Server in the cloud, no local installation of any dependencies is required, just fill in the following URL in the AI client:

https://seedance.mcp.acedata.cloud/mcp

Authentication method: Add Authorization: Bearer your API Token in the request header (Claude.ai completes this automatically via OAuth, no manual token entry required).

Claude.ai (Web Version, OAuth Login, Easiest)

  1. Open Claude.ai → Bottom left Customize → Connectors → Add More
  2. Enter the URL: https://seedance.mcp.acedata.cloud/mcp
  3. Complete OAuth authorization login (automatically redirects to 辰汐ai login page)
  4. Return to the chat interface, and the tool will be available for use

Claude Desktop

Edit the configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "seedance": {
      "type": "http",
      "url": "https://seedance.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer your API Token"
      }
    }
  }
}

After saving, restart Claude Desktop for the changes to take effect.

Claude Code (Terminal Command Line)

claude mcp add seedance --transport http https://seedance.mcp.acedata.cloud/mcp \
  -H "Authorization: Bearer your API Token"

VS Code (GitHub Copilot)

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

{
  "servers": {
    "seedance": {
      "type": "http",
      "url": "https://seedance.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer your API Token"
      }
    }
  }
}

Cursor

Create .cursor/mcp.json in the project root:

{
  "mcpServers": {
    "seedance": {
      "url": "https://seedance.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer your API Token"
      }
    }
  }
}

Other Clients Supporting MCP

Any client that supports the MCP Streamable HTTP protocol (Windsurf, Cline, ChatGPT Connectors, Gemini CLI, JetBrains AI Assistant, etc.) can connect by filling in the following two items:

  • URL: https://seedance.mcp.acedata.cloud/mcp
  • Header: Authorization: Bearer your API Token

Method 2: Local Run (pip / uvx Installation)

If you need to run offline, customize code, or deploy to an intranet, you can install the MCP Server locally and start it via stdio.

Installation

pip installation (recommended):

pip install mcp-seedance

Or install from source:

git clone https://github.com/AceDataCloud/SeedanceMCP.git
cd SeedanceMCP
pip install -e .

Once installed, you can start the service using the mcp-seedance command.

Using in Claude Desktop (Local)

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:

{
  "mcpServers": {
    "seedance": {
      "command": "mcp-seedance",
      "env": {
        "ACEDATACLOUD_API_TOKEN": "your API Token"
      }
    }
  }
}

If using uvx (no prior package installation required):

{
  "mcpServers": {
    "seedance": {
      "command": "uvx",
      "args": ["mcp-seedance"],
      "env": {
        "ACEDATACLOUD_API_TOKEN": "your API Token"
      }
    }
  }
}

After saving the configuration, restart Claude Desktop for the changes to take effect.

Using in VS Code / Cursor (Local)

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

{
  "servers": {
    "seedance": {
      "command": "mcp-seedance",
      "env": {
        "ACEDATACLOUD_API_TOKEN": "your API Token"
      }
    }
  }
}

Or use uvx:

{
  "servers": {
    "seedance": {
      "command": "uvx",
      "args": ["mcp-seedance"],
      "env": {
        "ACEDATACLOUD_API_TOKEN": "your API Token"
      }
    }
  }
}

Available Tools List

Tool Name Description
seedance_generate_video Generate video from text prompts
seedance_generate_video_from_image Generate video based on an image
seedance_get_task Query the status of a single task
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

Once configured, you can directly call these functions in the AI client using natural language, for example:

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

More Information