SeedanceMCP

A Model Context Protocol (MCP) server for AI video generation using ByteDance Seedance through the AceDataCloud API.

Generate AI videos directly from Claude, VS Code, or any MCP-compatible client.

Start with the hosted server

In a client that supports remote MCP OAuth, add https://seedance.mcp.acedata.cloud/mcp as an HTTP server.
Choose Connect / Sign in, log in to AceDataCloud, review the requested permissions, and authorize.
Enable the tools and ask for a playable video. You do not need to create or paste an API token for this route.

The server already supports OAuth discovery, dynamic client registration (DCR), and S256 PKCE. DCR registers the client application; you still sign in and approve access. Authorization does not make generation free. Review the consent screen: the media integration can read your profile and manage the applications and credentials used for API access. Usage is charged to your account.

Client compatibility

Client / mode	Start path	Boundary
Claude web / Desktop with remote custom connectors	Add the URL in the connector UI, then authorize	Availability and menu names depend on your plan and app version. The local Desktop JSON is for stdio; do not paste HTTP config there.
VS Code with native remote MCP support	Run MCP: Add Server, select HTTP, paste the URL, then follow authentication	Use a version with OAuth/DCR support. The optional AceDataCloud extension has its own API-key setup.
Other remote clients	Use the client's documented HTTP + OAuth flow	Support varies by client and version; an endpoint alone does not prove the client's login flow works.
Local stdio / self-hosted / clients without OAuth	Use the API Token path below	Keep the token in a local secret or environment variable; never in the server URL or Git.

Verify your first result

Generate a short video of clouds moving over a mountain, then retrieve the completed task and final video URL.

This is a reproducible example prompt, not a promised generation time or a recorded success. A connected server, tools/list, and a task ID only confirm setup/submission. Keep the task ID, wait for terminal success, then open or play the final media. Pending previews and failed tasks are not a completed result.

Charges and common failures

The MCP code is open source; hosted API generation is metered. Check current service pricing, model availability, account balance, and applicable terms before generating. No free allowance or commercial-use right is implied by installing this package.
Login loop / 401: reconnect using the client's authentication UI; for local usage check the token and its scope. Update a client that cannot discover or register an OAuth server.
403 / access denied: inspect the error and account permissions; a moderation rejection requires changing the input. Insufficient balance: inspect billing before retrying.
Pending / failed generation: poll the same task; read the final error. Do not repeatedly submit new tasks to fix polling. A new generation may incur a new charge.

API Token path

For local stdio or a client without OAuth, open your applications, sign in, choose the service, and create an API credential with the required scope. Configure ACEDATACLOUD_API_TOKEN locally, or use the client's documented Bearer-header setting. Use the local commands below for stdio; HTTP configuration formats are client-specific.

Features

Text to Video - Create AI-generated videos from text prompts
Image to Video - Animate images with first frame, last frame, and reference image control
Multiple Models - Support for Seedance 2.0 (incl. Fast/Mini, multimodal reference), 1.5 Pro, 1.0 Pro, 1.0 Pro Fast, 1.0 Lite T2V/I2V
Multiple Resolutions - 480p, 720p (default), 1080p, and 4k output (2.5 supports 1080p; 4k: doubao-seedance-2-0-260128 only)
Flexible Aspect Ratios - 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, and adaptive
Audio Generation - Generate synchronized audio for videos (1.5 Pro and 2.0 series)
Service Tiers - Default (priority) and Flex (cost-effective) processing
Task Tracking - Monitor generation progress and retrieve results

Tool Reference

Tool	Description
`seedance_generate_video`	Generate AI video from a text prompt using ByteDance Seedance.
`seedance_generate_video_from_image`	Generate AI video using reference images with ByteDance Seedance.
`seedance_get_task`	Query the status and result of a video generation task.
`seedance_get_tasks_batch`	Query multiple video generation tasks at once.
`seedance_list_models`	List all available Seedance models with their capabilities and pricing.
`seedance_list_resolutions`	List all available resolutions and aspect ratios for Seedance.
`seedance_list_actions`	List all available Seedance API actions and corresponding tools.

Run locally with an API token

If you prefer to run the server on your own machine:

# Install from PyPI
pip install mcp-seedance
# or
uvx mcp-seedance

# Set your API token
export ACEDATACLOUD_API_TOKEN="your_token_here"

# Run (stdio mode for Claude Desktop / local clients)
mcp-seedance

# Run (HTTP mode for remote access)
mcp-seedance --transport http --port 8000

Claude Desktop (Local)

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

Docker (Self-Hosting)

docker pull ghcr.io/acedatacloud/mcp-seedance:latest
docker run -p 8000:8000 ghcr.io/acedatacloud/mcp-seedance:latest

Clients connect with their own Bearer token — the server extracts the token from each request's Authorization header.

Available Tools

Video Generation

Tool	Description
`seedance_generate_video`	Generate video from a text prompt
`seedance_generate_video_from_image`	Generate video using reference/start/end images

Tasks

Tool	Description
`seedance_get_task`	Query a single task status
`seedance_get_tasks_batch`	Query multiple tasks at once

Information

Tool	Description
`seedance_list_models`	List available Seedance models
`seedance_list_resolutions`	List available output resolutions
`seedance_list_actions`	List available API actions

Usage Examples

Generate Video from Prompt

User: Create a video of a cat playing with a ball of yarn

Claude: I'll generate a video for you.
[Calls seedance_generate_video with prompt="A cute cat playfully batting a ball of yarn"]

Animate an Image

User: Turn this image into a video: https://example.com/landscape.jpg

Claude: I'll create a video from your image.
[Calls seedance_generate_video_from_image with first_frame_url and appropriate prompt]

Generate with Audio

User: Create a video of rain falling with sound

Claude: I'll generate a video with synchronized audio.
[Calls seedance_generate_video with prompt="Rain falling on a quiet street" and generate_audio=True, model="doubao-seedance-1-5-pro-251215"]

Available Models

Model	Description	Features
`doubao-seedance-2-5-260628`	2.5	Up to 30s and 1080p, edit/extend, multimodal reference
`doubao-seedance-2-0-fast-260128`	2.0 Fast	Latest generation fast
`doubao-seedance-2-0-mini-260615`	2.0 Mini	Latest generation, lightweight, cheapest 2.0
`doubao-seedance-1-5-pro-251215`	1.5 Pro	Audio generation, T2V, I2V
`doubao-seedance-1-0-pro-250528`	1.0 Pro	High quality T2V, I2V
`doubao-seedance-1-0-pro-fast-251015`	1.0 Pro Fast	Faster generation
`doubao-seedance-1-0-lite-t2v-250428`	1.0 Lite T2V	Lightweight text-to-video
`doubao-seedance-1-0-lite-i2v-250428`	1.0 Lite I2V	Lightweight image-to-video

Available Aspect Ratios

Aspect Ratio	Description	Use Case
`16:9`	Landscape (default)	YouTube, TV, presentations
`9:16`	Portrait	TikTok, Instagram Reels
`1:1`	Square	Instagram posts
`4:3`	Traditional	Classic video format
`3:4`	Portrait traditional	Portrait content
`21:9`	Ultrawide	Cinematic content
`adaptive`	Adaptive	Auto-detect from image

Configuration

Environment Variables

Variable	Description	Default
`ACEDATACLOUD_API_TOKEN`	API token from AceDataCloud	Required
`ACEDATACLOUD_API_BASE_URL`	API base URL	`https://api.acedata.cloud`
`ACEDATACLOUD_OAUTH_CLIENT_ID`	OAuth client ID (hosted mode)	—
`ACEDATACLOUD_PLATFORM_BASE_URL`	Platform base URL	`https://platform.acedata.cloud`
`SEEDANCE_DEFAULT_MODEL`	Default model	`doubao-seedance-2-0-260128`
`SEEDANCE_DEFAULT_RESOLUTION`	Default resolution	`720p`
`SEEDANCE_DEFAULT_RATIO`	Default aspect ratio	`16:9`
`SEEDANCE_DEFAULT_DURATION`	Default duration (seconds)	`5`
`SEEDANCE_REQUEST_TIMEOUT`	Request timeout in seconds	`1800`
`LOG_LEVEL`	Logging level	`INFO`

Command Line Options

mcp-seedance --help

Options:
  --version          Show version
  --transport        Transport mode: stdio (default) or http
  --port             Port for HTTP transport (default: 8000)

Development

Setup Development Environment

# Clone repository
git clone https://github.com/AceDataCloud/SeedanceMCP.git
cd SeedanceMCP

# Create virtual environment
python -m venv .venv
source .venv/bin/activate  # or `.venv\Scripts\activate` on Windows

# Install with dev dependencies
pip install -e ".[dev,test]"

Run Tests

# Run unit tests
pytest

# Run with coverage
pytest --cov=core --cov=tools

# Run integration tests (requires API token)
pytest tests/test_integration.py -m integration

Code Quality

# Format code
ruff format .

# Lint code
ruff check .

# Type check
mypy core tools

Build & Publish

# Install build dependencies
pip install -e ".[release]"

# Build package
python -m build

# Upload to PyPI
twine upload dist/*

Project Structure

SeedanceMCP/
├── core/                   # Core modules
│   ├── __init__.py
│   ├── client.py          # HTTP client for Seedance API
│   ├── config.py          # Configuration management
│   ├── exceptions.py      # Custom exceptions
│   ├── server.py          # MCP server initialization
│   ├── types.py           # Type definitions
│   └── utils.py           # Utility functions
├── tools/                  # MCP tool definitions
│   ├── __init__.py
│   ├── video_tools.py     # Video generation tools
│   ├── task_tools.py      # Task query tools
│   └── info_tools.py      # Information tools
├── prompts/                # MCP prompts
│   └── __init__.py        # Prompt templates
├── tests/                  # Test suite
│   ├── conftest.py
│   ├── test_client.py
│   ├── test_config.py
│   ├── test_integration.py
│   └── test_utils.py
├── deploy/                 # Deployment configs
│   └── production/
│       ├── deployment.yaml
│       ├── ingress.yaml
│       └── service.yaml
├── .env.example           # Environment template
├── .gitignore
├── CHANGELOG.md
├── Dockerfile             # Docker image for HTTP mode
├── docker-compose.yaml    # Docker Compose config
├── LICENSE
├── main.py                # Entry point
├── pyproject.toml         # Project configuration
└── README.md

API Reference

This server wraps the AceDataCloud Seedance API:

Seedance Videos API - Video generation
Seedance Tasks API - Task queries

Contributing

Contributions are welcome! Please:

Fork the repository
Create a feature branch (git checkout -b feature/amazing)
Commit your changes (git commit -m 'Add amazing feature')
Push to the branch (git push origin feature/amazing)
Open a Pull Request

Documentation

License

MIT License - see LICENSE for details.

Links

Made with love by AceDataCloud

Metadata

Release files for mcp-seedance 2026.10.4.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for mcp-seedance 2026.10.4.0
File	Size	Uploaded
mcp_seedance-2026.10.4.0.tar.gz	42.6 kB	Oct 4, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for mcp-seedance 2026.10.4.0
File	Interpreter	ABI	Platform	Reset
mcp_seedance-2026.10.4.0-py3-none-any.whl 33.4 kB Oct 4, 2026	Python 3	none	any	Details

Total release size: 76.1 kB

Release files / mcp_seedance-2026.10.4.0.tar.gz

Download URL	mcp_seedance-2026.10.4.0.tar.gz
Size	42.6 kB
Tags	Source
SHA-256 checksum How to use checksums	`99d0a981434b9680fa6953d6fa544dea6ea8a2f842eb897851a690958ccc4b26`
BLAKE2b-256 checksum How to use checksums	`08b73863fcaa05100c4bbbec02dcb09682d97c13badbca527952624def6f9ced`
Upload date	Oct 4, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.0.1 CPython/3.12.3`

Release files / mcp_seedance-2026.10.4.0-py3-none-any.whl

Download URL	mcp_seedance-2026.10.4.0-py3-none-any.whl
Size	33.4 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`e4021df4d6db5272dd4c9ec80f878b796b455dc4136766143031bb2da3a8dc9f`
BLAKE2b-256 checksum How to use checksums	`09a8f1559df04d700faadfdcafe6f003cdc8adb18718efaec4ae942e27b4655a`
Upload date	Oct 4, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.0.1 CPython/3.12.3`