Skip to main content
Glama
deenesjakoruzh
AceDataCloud

SeedanceMCP

by AceDataCloud
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

SeedanceMCP

PyPI version PyPI downloads Python 3.10+ License: MIT MCP

一个用于通过 AceDataCloud API 使用 字节跳动 Seedance 进行 AI 视频生成的 模型上下文协议 (MCP) 服务器。

直接从 Claude、VS Code 或任何兼容 MCP 的客户端生成 AI 视频。

功能特性

  • 文生视频 (Text to Video) - 根据文本提示词创建 AI 生成的视频

  • 图生视频 (Image to Video) - 通过首帧、尾帧和参考图像控制来制作动画

  • 多种模型 - 支持 Seedance 1.5 Pro、1.0 Pro、1.0 Pro Fast、1.0 Lite T2V/I2V

  • 多种分辨率 - 支持 480p、720p（默认）和 1080p 输出

  • 灵活的宽高比 - 16:9、9:16、1:1、4:3、3:4、21:9 以及自适应

  • 音频生成 - 为视频生成同步音频 (1.5 Pro)

  • 服务层级 - 默认（优先）和 Flex（高性价比）处理模式

  • 任务追踪 - 监控生成进度并获取结果

Related MCP server: seedance-2-mcp

工具参考

工具

描述

seedance_generate_video

使用字节跳动 Seedance 根据文本提示词生成 AI 视频。

seedance_generate_video_from_image

使用字节跳动 Seedance 通过参考图像生成 AI 视频。

seedance_get_task

查询视频生成任务的状态和结果。

seedance_get_tasks_batch

同时查询多个视频生成任务。

seedance_list_models

列出所有可用的 Seedance 模型及其功能和定价。

seedance_list_resolutions

列出 Seedance 所有可用的分辨率和宽高比。

seedance_list_actions

列出所有可用的 Seedance API 操作及对应的工具。

快速开始

1. 获取您的 API Token

  1. 在 AceDataCloud 平台 注册

  2. 前往 API 文档页面

  3. 点击 “Acquire” 获取您的 API token

  4. 复制该 token 以供下方使用

2. 使用托管服务器（推荐）

AceDataCloud 托管了一个受管理的 MCP 服务器 —— 无需本地安装。

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

所有请求都需要 Bearer token。请使用第 1 步中获取的 API token。

Claude.ai

通过 OAuth 直接在 Claude.ai 上连接 —— 无需 API token：

  1. 前往 Claude.ai 设置 → 集成 → 添加更多

  2. 输入服务器 URL：https://seedance.mcp.acedata.cloud/mcp

  3. 完成 OAuth 登录流程

  4. 开始在对话中使用这些工具

Claude Desktop

添加到您的配置文件（macOS 上为 ~/Library/Application Support/Claude/claude_desktop_config.json）：

{
  "mcpServers": {
    "seedance": {
      "type": "streamable-http",
      "url": "https://seedance.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Cursor / Windsurf

添加到您的 MCP 配置文件（.cursor/mcp.json 或 .windsurf/mcp.json）：

{
  "mcpServers": {
    "seedance": {
      "type": "streamable-http",
      "url": "https://seedance.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

VS Code (Copilot)

添加到您的 VS Code MCP 配置文件（.vscode/mcp.json）：

{
  "servers": {
    "seedance": {
      "type": "streamable-http",
      "url": "https://seedance.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

或者为 VS Code 安装 Ace Data Cloud MCP 扩展，该扩展一键集成了所有 15 个 MCP 服务器。

JetBrains IDEs

  1. 前往 设置 → 工具 → AI Assistant → 模型上下文协议 (MCP)

  2. 点击 添加 → HTTP

  3. 粘贴：

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

Claude Code

Claude Code 原生支持 MCP 服务器：

claude mcp add seedance --transport http https://seedance.mcp.acedata.cloud/mcp \
  -h "Authorization: Bearer YOUR_API_TOKEN"

或者添加到项目的 .mcp.json 中：

{
  "mcpServers": {
    "seedance": {
      "type": "streamable-http",
      "url": "https://seedance.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Cline

添加到 Cline 的 MCP 设置（.cline/mcp_settings.json）：

{
  "mcpServers": {
    "seedance": {
      "type": "streamable-http",
      "url": "https://seedance.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Amazon Q Developer

添加到您的 MCP 配置中：

{
  "mcpServers": {
    "seedance": {
      "type": "streamable-http",
      "url": "https://seedance.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Roo Code

添加到 Roo Code 的 MCP 设置中：

{
  "mcpServers": {
    "seedance": {
      "type": "streamable-http",
      "url": "https://seedance.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Continue.dev

添加到 .continue/config.yaml：

mcpServers:
  - name: seedance
    type: streamable-http
    url: https://seedance.mcp.acedata.cloud/mcp
    headers:
      Authorization: "Bearer YOUR_API_TOKEN"

Zed

添加到 Zed 的设置（~/.config/zed/settings.json）：

{
  "language_models": {
    "mcp_servers": {
      "seedance": {
        "url": "https://seedance.mcp.acedata.cloud/mcp",
        "headers": {
          "Authorization": "Bearer YOUR_API_TOKEN"
        }
      }
    }
  }
}

cURL 测试

# Health check (no auth required)
curl https://seedance.mcp.acedata.cloud/health

# MCP initialize
curl -X POST https://seedance.mcp.acedata.cloud/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}}}'

3. 或者本地运行（替代方案）

如果您更喜欢在自己的机器上运行服务器：

# 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 (本地)

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

Docker (自托管)

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

客户端使用各自的 Bearer token 进行连接 —— 服务器会从每个请求的 Authorization 标头中提取 token。

可用工具

视频生成

工具

描述

seedance_generate_video

根据文本提示词生成视频

seedance_generate_video_from_image

使用参考/起始/结束图像生成视频

任务

工具

描述

seedance_get_task

查询单个任务状态

seedance_get_tasks_batch

同时查询多个任务

信息

工具

描述

seedance_list_models

列出可用的 Seedance 模型

seedance_list_resolutions

列出可用的输出分辨率

seedance_list_actions

列出可用的 API 操作

使用示例

根据提示词生成视频

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"]

制作图像动画

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]

生成带音频的视频

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"]

可用模型

模型

描述

功能

doubao-seedance-2-0-260128

2.0

最新生成质量

doubao-seedance-2-0-fast-260128

2.0 Fast

最新快速生成

doubao-seedance-1-5-pro-251215

1.5 Pro

音频生成, T2V, I2V

doubao-seedance-1-0-pro-250528

1.0 Pro (默认)

高质量 T2V, I2V

doubao-seedance-1-0-pro-fast-251015

1.0 Pro Fast

更快的生成速度

doubao-seedance-1-0-lite-t2v-250428

1.0 Lite T2V

轻量级文生视频

doubao-seedance-1-0-lite-i2v-250428

1.0 Lite I2V

轻量级图生视频

可用宽高比

宽高比

描述

使用场景

16:9

横屏 (默认)

YouTube, 电视, 演示文稿

9:16

竖屏

TikTok, Instagram Reels

1:1

正方形

Instagram 帖子

4:3

传统

经典视频格式

3:4

传统竖屏

竖屏内容

21:9

超宽屏

电影内容

adaptive

自适应

从图像自动检测

配置

环境变量

变量

描述

默认值

ACEDATACLOUD_API_TOKEN

AceDataCloud 的 API token

必需

ACEDATACLOUD_API_BASE_URL

API 基础 URL

https://api.acedata.cloud

ACEDATACLOUD_OAUTH_CLIENT_ID

OAuth 客户端 ID (托管模式)

—

ACEDATACLOUD_PLATFORM_BASE_URL

平台基础 URL

https://platform.acedata.cloud

SEEDANCE_DEFAULT_MODEL

默认模型

doubao-seedance-1-0-pro-250528

SEEDANCE_DEFAULT_RESOLUTION

默认分辨率

720p

SEEDANCE_DEFAULT_RATIO

默认宽高比

16:9

SEEDANCE_DEFAULT_DURATION

默认时长 (秒)

5

SEEDANCE_REQUEST_TIMEOUT

请求超时 (秒)

1800

LOG_LEVEL

日志级别

INFO

命令行选项

mcp-seedance --help

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

开发

设置开发环境

# 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]"

运行测试

# 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

代码质量

# Format code
ruff format .

# Lint code
ruff check .

# Type check
mypy core tools

构建与发布

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

# Build package
python -m build

# Upload to PyPI
twine upload dist/*

项目结构

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 参考

此服务器封装了 AceDataCloud Seedance API：

贡献

欢迎贡献！请：

  1. Fork 本仓库

  2. 创建功能分支 (git checkout -b feature/amazing)

  3. 提交您的更改 (git commit -m 'Add amazing feature')

  4. 推送到分支 (git push origin feature/amazing)

  5. 开启 Pull Request

许可证

MIT 许可证 - 详情请参阅 LICENSE。

链接

由 AceDataCloud 用心制作

Available Tools

7 tools
seedance_generate_videoAInspect

Generate AI video from a text prompt using ByteDance Seedance.

This is the simplest way to create video - just describe what you want and
Seedance will generate a high-quality AI video.

Use this when:
- You want to create a video from a text description
- You don't have reference images
- You want quick text-to-video generation

For using reference images (first/last frame, reference), use
seedance_generate_video_from_image instead.

Returns:
    Task ID and generated video information including URLs and metadata.
ParametersJSON Schema
NameRequiredDescriptionDefault
seedNoRandom seed for reproducible generation. Range: -1 to 4294967295. Use -1 for random. Default is -1.
modelNoModel version to use. Options: 'doubao-seedance-2-5-260628' (latest flagship, up to 30 seconds, multimodal reference, edit/extend, default), 'doubao-seedance-2-0-260128' (highest resolution, supports 4k), 'doubao-seedance-2-0-fast-260128' (latest generation, faster, up to 720p), 'doubao-seedance-2-0-mini-260615' (latest generation, lightweight, cheapest within the 2.0 series, up to 720p), 'doubao-seedance-1-5-pro-251215' (1.5 flagship, supports audio), 'doubao-seedance-1-0-pro-250528' (1.0 standard), 'doubao-seedance-1-0-pro-fast-251015' (1.0 fast, cost-optimized), 'doubao-seedance-1-0-lite-t2v-250428' (lightweight text-to-video), 'doubao-seedance-1-0-lite-i2v-250428' (lightweight image-to-video).doubao-seedance-2-0-260128
ratioNoVideo aspect ratio. Options: '16:9' (landscape, default), '9:16' (portrait), '1:1' (square), '4:3', '3:4', '21:9' (ultrawide), 'adaptive'.16:9
toolsNoOptional Seedance 2.5 web search tool configuration.
framesNoFrame count for the generated video (1.0 series only). Must satisfy 25+4n (e.g. 29, 33, 37, ..., 289). Mutually exclusive with 'duration'.
promptYesDescription of the video to generate. Max 1000 characters. Be descriptive about the scene, motion, style, and mood. You can also include inline parameters like '--rs 720p --rt 16:9 --dur 5'. Examples: 'A cat walking through a garden with butterflies', 'Cinematic aerial shot of mountains at sunset'
durationNoVideo duration in seconds. 1.0 series: 2–12; 1.5 Pro: 4–12; 2.0 series: 4–15; 2.5: 4–30. Use -1 for auto-duration (1.5 Pro and 2.x). Default is 5. Mutually exclusive with 'frames'.
priorityNoSeedance 2.5 task priority from 0 to 9.
watermarkNoIf true, add a watermark to the video. Default is false.
resolutionNoVideo resolution. Options: '480p', '720p' (default), '1080p', '4k'. '4k' is supported only by 'doubao-seedance-2-0-260128'; '2-5' maxes out at '1080p'; '2-0-fast' and '2-0-mini' max out at '720p'.720p
callback_urlNoWebhook callback URL for asynchronous notifications. When provided, the API returns immediately with a task_id and calls this URL when the video is generated.
camera_fixedNoIf true, keep the camera fixed during generation. Default is false.
output_formatNoSeedance 2.5 output format: mp4 or mov.
generate_audioNoIf true, generate audio along with the video. Supported by 'doubao-seedance-1-5-pro-251215' and the 'doubao-seedance-2-0' series; other models ignore it. Approximately doubles the cost. Default is false.
return_last_frameNoIf true, also return the last frame of the generated video as an image URL. Useful for video extension workflows. Default is false.
safety_identifierNoStable anonymous end-user identifier. Do not use personal information.
execution_expires_afterNoTask timeout threshold in seconds. Default is 172800 (48 hours).

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the behavioral disclosure burden. It does add a Returns clause mentioning task ID, video URLs, and metadata, which hints at task-based behavior. However, it omits important operational traits such as generation taking significant time and the likely need to poll or wait for the final video.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loaded: action, use cases, alternative, and return summary come in a readable order. The 'simplest way / high-quality' sentence is slightly promotional and redundant with the first sentence, but it does not meaningfully inflate the length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 17-parameter tool, the input schema covers most details and an output schema presumably documents return structure. The description covers primary use cases and sibling routing, but it does not explain how to retrieve the final result, e.g., via seedance_get_task, or warn about long-running generation. It is adequate but has clear gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the schema already documents all 17 parameters with defaults, enums, and model-specific constraints. The description adds little beyond identifying the prompt as the core input and clarifying this is the text-only variant, so the parameter burden is adequately carried by the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Generate AI video from a text prompt using ByteDance Seedance.' It also names the sibling seedance_generate_video_from_image, so an agent can immediately distinguish text-to-video generation from image-conditioned generation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'Use this when' bullets clearly define the conditions: creating video from text, no reference images, and quick text-to-video generation. It explicitly directs image-reference workflows to seedance_generate_video_from_image instead, which is excellent routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

seedance_generate_video_from_imageAInspect

Generate AI video using reference images with ByteDance Seedance.

This allows you to control the video by specifying first frame, last frame,
or reference images. Seedance will generate smooth motion based on the inputs.

Use this when:
- You have a specific image you want to animate
- You want to create a video transition between two images
- You need style guidance from reference images
- You need precise control over the video's visual content

Note: reference_image_urls cannot be combined with first_frame_url/last_frame_url.
At least one image input must be provided.

Returns:
    Task ID and generated video information including URLs and metadata.
ParametersJSON Schema
NameRequiredDescriptionDefault
seedNoRandom seed. -1 for random. Default is -1.
modelNoModel version to use. Use 'doubao-seedance-2-0-260128' (default) for latest-generation quality and multimodal reference, 'doubao-seedance-2-0-fast-260128' or 'doubao-seedance-2-0-mini-260615' for faster/cheaper 2.0, or a 1.x model such as 'doubao-seedance-1-0-lite-i2v-250428' for lightweight I2V.doubao-seedance-2-0-260128
ratioNoVideo aspect ratio. Use 'adaptive' to match your input image ratio.16:9
toolsNoOptional Seedance 2.5 web search tool configuration.
framesNoFrame count for the generated video (1.0 series only). Must satisfy 25+4n (e.g. 29, 33, 37, ..., 289). Mutually exclusive with 'duration'.
promptYesDescription of the video motion and content. Describe what should happen in the video, how objects should move, what transitions to include.
durationNoVideo duration in seconds. 1.0 series: 2–12; 1.5 Pro: 4–12; 2.0 series: 4–15; 2.5: 4–30. Use -1 for auto-duration (1.5 Pro and 2.x). Default is 5. Mutually exclusive with 'frames'.
priorityNoSeedance 2.5 task priority from 0 to 9.
resolutionNoVideo resolution. Options: '480p', '720p', '1080p', '4k'. '4k' is supported only by 'doubao-seedance-2-0-260128'; '2-5' maxes out at '1080p'; '2-0-fast' and '2-0-mini' max out at '720p'.720p
callback_urlNoWebhook callback URL for asynchronous notifications.
output_formatNoSeedance 2.5 output format: mp4 or mov.
generate_audioNoIf true, generate audio. Supported by 'doubao-seedance-1-5-pro-251215' and the Seedance 2.x series. Default is false.
last_frame_urlNoURL of the image to use as the last frame of the video. The video will animate towards this image. Supports https:// URLs or base64 data:image/... URIs.
first_frame_urlNoURL of the image to use as the first frame of the video. The video will animate from this image. Supports https:// URLs or base64 data:image/... URIs.
return_last_frameNoIf true, return the last frame of the generated video. Default is false.
safety_identifierNoStable anonymous end-user identifier. Do not use personal information.
reference_audio_urlsNoSeedance 2.0 only. Reference audio URLs (up to 3) for voice timbre / background music. Ignored by 1.x models.
reference_image_urlsNoList of reference image URLs for style/content guidance. For the Seedance 2.0 series these can be real-person / character references that keep the subject consistent (up to 9). These images influence the look but are not used as frames. Cannot be combined with first_frame_url or last_frame_url.
reference_video_urlsNoSeedance 2.0 only. Reference video URLs (up to 3) for subject, camera movement, motion or overall style. Ignored by 1.x models.
execution_expires_afterNoTask timeout threshold in seconds. Default is 172800 (48 hours).
omni_reference_task_typeNoSeedance 2.5 task type: auto, reference, edit, or extend.

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the behavioral disclosure burden. It discloses the mutual exclusivity constraint between reference images and frame URLs, and notes that at least one image must be provided. It also states the return value (task ID and video info). Though it doesn't detail async behavior or polling requirements, this is reasonable coverage for a generation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-organized with a lead sentence, usage bullets, a constraint note, and a returns section. It is slightly longer than strictly necessary but every section adds value, and the most critical constraint is called out explicitly near the end of the main text.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 21 parameters and no annotations, the description does a good job capturing the essential behavioral context: image input modes, mutual exclusivity, and required input. The return-value section is present, and the schema covers parameter details. Minor omissions like asynchronous/polling behavior are not fatal because the output schema provides return structure.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already explains every parameter. The description adds meaning by grouping input modes (first frame, last frame, reference images) and highlighting the interaction constraint among them. It doesn't restate each parameter but adds selection-level semantics that the flat schema lacks.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that this tool generates AI video from reference images using ByteDance Seedance, distinguishing it from the sibling seedance_generate_video (which presumably lacks image control). It explicitly names the input modes (first frame, last frame, reference images) and supports this with concrete usage cases.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit when-to-use bullet points and a critical exclusion rule: reference_image_urls cannot be combined with first_frame_url/last_frame_url. It also mandates at least one image input. This is strong guidance for tool selection and correct invocation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

seedance_get_taskAInspect

Query the status and result of a video generation task.

Use this to check if a generation is complete and retrieve the resulting
video URLs, thumbnails, and other metadata.

Use this when:
- You want to check if a generation has completed
- You need to retrieve video URLs from a previous generation
- You want to get the full details of a generated video

Task statuses:
- 'running': Generation is still in progress
- 'succeeded': Generation finished successfully
- 'failed': Generation failed (check error message)

Returns:
    Task status and generated video information including URLs and metadata.
ParametersJSON Schema
NameRequiredDescriptionDefault
task_idYesThe task ID returned from a generation request. This is the 'task_id' field from any seedance_generate_* tool response.

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations, but description covers task statuses and error handling. Read-only nature implied, but no mention of auth or rate limits; adequate for simplicity.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Efficient use of bullet points for statuses and returns. Front-loaded key purpose, no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given output schema exists and tool is simple, description covers all necessary context: statuses, return content, and usage rationale.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage 100% with parameter description. Description adds value by specifying source of task_id (from generation response).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb 'Query' and resource 'status and result of a video generation task'. Clearly distinguishes from sibling generation and list tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit usage scenarios (check completion, retrieve URLs, get details). No explicit when-not, but context is clear for a query tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

seedance_get_tasks_batchAInspect

Query multiple video generation tasks at once.

Efficiently check the status of multiple tasks in a single request.
More efficient than calling seedance_get_task multiple times.

Use this when:
- You have multiple pending generations to check
- You want to get status of several videos at once
- You're tracking a batch of generations

Returns:
    Status and video information for all queried tasks.
ParametersJSON Schema
NameRequiredDescriptionDefault
task_idsYesList of task IDs to query. Maximum recommended batch size is 50 tasks.

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, but description implies a safe read operation by calling it a query. Mentions batch limit in schema, which adds practical info. Could explicitly state read-only nature.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Concise, front-loaded with purpose, then usage guidelines, then returns. Every sentence adds value with no fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has a simple interface (1 param, output schema exists). Description covers all necessary aspects: purpose, usage context, and return summary. Minor gap: no explicit safety statement.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers parameter semantics fully (100% coverage) with description of task_ids and batch limit. Main description adds only context about batching and returns, but no extra parameter meaning beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Query multiple video generation tasks at once' and distinguishes itself from sibling tool `seedance_get_task` by emphasizing batching efficiency.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly lists when to use the tool with bullet points and compares to the sibling tool, stating 'More efficient than calling seedance_get_task multiple times'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

seedance_list_actionsAInspect

List all available Seedance API actions and corresponding tools.

Reference guide for what each action does and which tool to use.
Helpful for understanding the full capabilities of the Seedance MCP.

Returns:
    Categorized list of all actions and their corresponding tools.
ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Clearly describes the operation as a listing of actions/tools returning a categorized list, which is transparent for a read-only operation; no annotations provided.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Concise three-sentence description front-loads the purpose and return value, with no unnecessary information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given zero parameters and presence of an output schema, the description adequately covers purpose, output, and utility without gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters, but description adds meaningful context about the return value (categorized list of actions and tools) beyond the empty schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states it lists all Seedance API actions and corresponding tools, distinguishing it from sibling tools that generate videos, get tasks, or list models.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implied use as a reference guide for understanding capabilities, but no explicit when-to-use or when-not-to-use guidance compared to alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

seedance_list_modelsAInspect

List all available Seedance models with their capabilities and pricing.

Shows all available model options with their features, strengths, and costs.
Use this to understand which model to choose for your video generation.

Returns:
    Table of all models with descriptions, capabilities, and pricing.
ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses that the tool lists models with capabilities and pricing, implying a read-only operation with no side effects. This is adequate for a simple list tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences, each contributing to the purpose, usage, and return value. It is concise without being overly terse, though some minor redundancy exists ('Shows all available model options' repeats the first sentence).

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given zero parameters and the existence of an output schema, the description adequately covers the tool's purpose, usage, and return value. No further information is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, and schema coverage is 100%. The baseline for 0 parameters is 4. The description does not need to add parameter information.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'List all available Seedance models with their capabilities and pricing.' This is a specific verb+resource combination that distinguishes it from sibling tools like seedance_generate_video or seedance_get_task.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description includes 'Use this to understand which model to choose for your video generation,' providing clear context for when to use the tool. It does not explicitly state when not to use alternatives, but the purpose is simple enough.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

seedance_list_resolutionsAInspect

List all available resolutions and aspect ratios for Seedance.

Shows all available resolution and aspect ratio options with use cases.

Returns:
    Tables of resolutions and aspect ratios with descriptions.
ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description transparently states it returns tables of resolutions and aspect ratios with descriptions. It adds value beyond a simple 'list' by mentioning use cases and descriptions, though it does not detail freshness or caching behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with two sentences and a 'Returns:' clause. Every sentence adds value, and the structure is front-loaded with the primary action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given zero parameters and an output schema, the description fully covers what the tool does and returns. It is complete for a simple listing tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters exist, and schema description coverage is 100%. Per baseline, score 4 is appropriate as the description does not need to add parameter info.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states the tool lists all available resolutions and aspect ratios for Seedance. It clearly distinguishes itself from sibling tools like seedance_list_models or seedance_list_actions by focusing on resolution options.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context (before generating a video) but provides no explicit when/when-not guidance or alternatives. The agent can infer use, but lacks explicit direction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev0.1.11
    • Changedseedance_generate_video_from_image2 fields changed
      • changedInput schema / properties / omni_reference_task_type / anyOf
        Previous value: -[
-  {
-    "enum": [
-      "auto",
-      "edit",
-      "extend"
-    ],
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "enum": [
+      "auto",
+      "reference",
+      "edit",
+      "extend"
+    ],
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
      • changedInput schema / properties / omni_reference_task_type / description
        Previous value: -"Seedance 2.5 task type: auto, edit, or extend."New value: +"Seedance 2.5 task type: auto, reference, edit, or extend."
  2. 2 tool updatesv0.1.10
    • Changedseedance_generate_video2 fields changed
      • addedInput schema / properties / execution_expires_after / maximum
        Added value: +259200
      • addedInput schema / properties / execution_expires_after / minimum
        Added value: +3600
    • Changedseedance_generate_video_from_image2 fields changed
      • addedInput schema / properties / execution_expires_after / maximum
        Added value: +259200
      • addedInput schema / properties / execution_expires_after / minimum
        Added value: +3600
  3. 2 tool updatesv0.1.9
    • Changedseedance_generate_video6 fields changed
      • addedInput schema / $defs
        Added value: +{
+  "SeedanceWebSearchTool": {
+    "additionalProperties": false,
+    "description": "Seedance web search tool configuration.",
+    "properties": {
+      "limit": {
+        "default": 10,
+        "maximum": 50,
+        "minimum": 1,
+        "title": "Limit",
+        "type": "integer"
+      },
+      "max_keyword": {
+        "anyOf": [
+          {
+            "maximum": 50,
+            "minimum": 1,
+            "type": "integer"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Max Keyword"
+      },
+      "sources": {
+        "anyOf": [
+          {
+            "items": {
+              "enum": [
+                "toutiao",
+                "douyin",
+                "moji",
+                "search_engine"
+              ],
+              "type": "string"
+            },
+            "type": "array"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Sources"
+      },
+      "type": {
+        "const": "web_search",
+        "title": "Type",
+        "type": "string"
+      }
+    },
+    "required": [
+      "type"
+    ],
+    "title": "SeedanceWebSearchTool",
+    "type": "object"
+  }
+}
      • addedInput schema / properties / priority
        Added value: +{
+  "default": 0,
+  "description": "Seedance 2.5 task priority from 0 to 9.",
+  "maximum": 9,
+  "minimum": 0,
+  "title": "Priority",
+  "type": "integer"
+}
      • changedInput schema / properties / resolution / description
        Previous value: -"Video resolution. Options: '480p', '720p' (default), '1080p', '4k'. '4k' is supported only by 'doubao-seedance-2-0-260128'; '2-0-fast' and '2-0-mini' max out at '720p'."New value: +"Video resolution. Options: '480p', '720p' (default), '1080p', '4k'. '4k' is supported only by 'doubao-seedance-2-0-260128'; '2-5' maxes out at '1080p'; '2-0-fast' and '2-0-mini' max out at '720p'."
      • addedInput schema / properties / safety_identifier
        Added value: +{
+  "anyOf": [
+    {
+      "maxLength": 64,
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Stable anonymous end-user identifier. Do not use personal information.",
+  "title": "Safety Identifier"
+}
      • changedInput schema / properties / tools / anyOf
        Previous value: -[
-  {
-    "items": {
-      "additionalProperties": true,
-      "type": "object"
-    },
-    "type": "array"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "items": {
+      "$ref": "#/$defs/SeedanceWebSearchTool"
+    },
+    "maxItems": 1,
+    "type": "array"
+  },
+  {
+    "type": "null"
+  }
+]
      • changedInput schema / properties / tools / description
        Previous value: -"Optional Seedance 2.5 tool configuration objects."New value: +"Optional Seedance 2.5 web search tool configuration."
    • Changedseedance_generate_video_from_image6 fields changed
      • addedInput schema / $defs
        Added value: +{
+  "SeedanceWebSearchTool": {
+    "additionalProperties": false,
+    "description": "Seedance web search tool configuration.",
+    "properties": {
+      "limit": {
+        "default": 10,
+        "maximum": 50,
+        "minimum": 1,
+        "title": "Limit",
+        "type": "integer"
+      },
+      "max_keyword": {
+        "anyOf": [
+          {
+            "maximum": 50,
+            "minimum": 1,
+            "type": "integer"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Max Keyword"
+      },
+      "sources": {
+        "anyOf": [
+          {
+            "items": {
+              "enum": [
+                "toutiao",
+                "douyin",
+                "moji",
+                "search_engine"
+              ],
+              "type": "string"
+            },
+            "type": "array"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Sources"
+      },
+      "type": {
+        "const": "web_search",
+        "title": "Type",
+        "type": "string"
+      }
+    },
+    "required": [
+      "type"
+    ],
+    "title": "SeedanceWebSearchTool",
+    "type": "object"
+  }
+}
      • addedInput schema / properties / priority
        Added value: +{
+  "default": 0,
+  "description": "Seedance 2.5 task priority from 0 to 9.",
+  "maximum": 9,
+  "minimum": 0,
+  "title": "Priority",
+  "type": "integer"
+}
      • changedInput schema / properties / resolution / description
        Previous value: -"Video resolution. Options: '480p', '720p', '1080p', '4k'. '4k' is supported only by 'doubao-seedance-2-0-260128'; '2-0-fast' and '2-0-mini' max out at '720p'."New value: +"Video resolution. Options: '480p', '720p', '1080p', '4k'. '4k' is supported only by 'doubao-seedance-2-0-260128'; '2-5' maxes out at '1080p'; '2-0-fast' and '2-0-mini' max out at '720p'."
      • addedInput schema / properties / safety_identifier
        Added value: +{
+  "anyOf": [
+    {
+      "maxLength": 64,
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Stable anonymous end-user identifier. Do not use personal information.",
+  "title": "Safety Identifier"
+}
      • changedInput schema / properties / tools / anyOf
        Previous value: -[
-  {
-    "items": {
-      "additionalProperties": true,
-      "type": "object"
-    },
-    "type": "array"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "items": {
+      "$ref": "#/$defs/SeedanceWebSearchTool"
+    },
+    "maxItems": 1,
+    "type": "array"
+  },
+  {
+    "type": "null"
+  }
+]
      • changedInput schema / properties / tools / description
        Previous value: -"Optional Seedance 2.5 tool configuration objects."New value: +"Optional Seedance 2.5 web search tool configuration."
  4. 2 tool updatesv0.1.8
    • Changedseedance_generate_video9 fields changed
      • changedInput schema / properties / duration / anyOf
        Previous value: -[
-  {
-    "maximum": 15,
-    "minimum": 2,
-    "type": "integer"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "maximum": 30,
+    "minimum": -1,
+    "type": "integer"
+  },
+  {
+    "type": "null"
+  }
+]
      • changedInput schema / properties / duration / description
        Previous value: -"Video duration in seconds. Range: 2-15 (Seedance 2.0 supports 4-15). Default is 5. Mutually exclusive with 'frames'."New value: +"Video duration in seconds. 1.0 series: 2–12; 1.5 Pro: 4–12; 2.0 series: 4–15; 2.5: 4–30. Use -1 for auto-duration (1.5 Pro and 2.x). Default is 5. Mutually exclusive with 'frames'."
      • changedInput schema / properties / frames / anyOf
        Previous value: -[
-  {
-    "type": "integer"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "maximum": 289,
+    "minimum": 29,
+    "type": "integer"
+  },
+  {
+    "type": "null"
+  }
+]
      • changedInput schema / properties / frames / description
        Previous value: -"Frame count for the generated video. Must satisfy 25+4n (e.g. 29, 33, 37, ..., 361). Mutually exclusive with 'duration'."New value: +"Frame count for the generated video (1.0 series only). Must satisfy 25+4n (e.g. 29, 33, 37, ..., 289). Mutually exclusive with 'duration'."
      • changedInput schema / properties / model / description
        Previous value: -"Model version to use. Options: 'doubao-seedance-2-0-260128' (latest generation, highest quality, supports 4k and multimodal reference, default), 'doubao-seedance-2-0-fast-260128' (latest generation, faster, up to 720p), 'doubao-seedance-2-0-mini-260615' (latest generation, lightweight, cheapest within the 2.0 series, up to 720p), 'doubao-seedance-1-5-pro-251215' (1.5 flagship, supports audio), 'doubao-seedance-1-0-pro-250528' (1.0 standard), 'doubao-seedance-1-0-pro-fast-251015' (1.0 fast, cost-optimized), 'doubao-seedance-1-0-lite-t2v-250428' (lightweight text-to-video), 'doubao-seedance-1-0-lite-i2v-250428' (lightweight image-to-video)."New value: +"Model version to use. Options: 'doubao-seedance-2-5-260628' (latest flagship, up to 30 seconds, multimodal reference, edit/extend, default), 'doubao-seedance-2-0-260128' (highest resolution, supports 4k), 'doubao-seedance-2-0-fast-260128' (latest generation, faster, up to 720p), 'doubao-seedance-2-0-mini-260615' (latest generation, lightweight, cheapest within the 2.0 series, up to 720p), 'doubao-seedance-1-5-pro-251215' (1.5 flagship, supports audio), 'doubao-seedance-1-0-pro-250528' (1.0 standard), 'doubao-seedance-1-0-pro-fast-251015' (1.0 fast, cost-optimized), 'doubao-seedance-1-0-lite-t2v-250428' (lightweight text-to-video), 'doubao-seedance-1-0-lite-i2v-250428' (lightweight image-to-video)."
      • changedInput schema / properties / model / enum
        Previous value: -[
-  "doubao-seedance-2-0-260128",
-  "doubao-seedance-2-0-fast-260128",
-  "doubao-seedance-2-0-mini-260615",
-  "doubao-seedance-1-5-pro-251215",
-  "doubao-seedance-1-0-pro-250528",
-  "doubao-seedance-1-0-pro-fast-251015",
-  "doubao-seedance-1-0-lite-t2v-250428",
-  "doubao-seedance-1-0-lite-i2v-250428"
-]New value: +[
+  "doubao-seedance-2-5-260628",
+  "doubao-seedance-2-0-260128",
+  "doubao-seedance-2-0-fast-260128",
+  "doubao-seedance-2-0-mini-260615",
+  "doubao-seedance-1-5-pro-251215",
+  "doubao-seedance-1-0-pro-250528",
+  "doubao-seedance-1-0-pro-fast-251015",
+  "doubao-seedance-1-0-lite-t2v-250428",
+  "doubao-seedance-1-0-lite-i2v-250428"
+]
      • addedInput schema / properties / output_format
        Added value: +{
+  "anyOf": [
+    {
+      "enum": [
+        "mp4",
+        "mov"
+      ],
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Seedance 2.5 output format: mp4 or mov.",
+  "title": "Output Format"
+}
      • removedInput schema / properties / service_tier
        Removed value: -{
-  "default": "default",
-  "description": "Service tier. 'default' for standard processing, 'flex' for 50%% cheaper but slower processing. Default is 'default'.",
-  "enum": [
-    "default",
-    "flex"
-  ],
-  "title": "Service Tier",
-  "type": "string"
-}
      • addedInput schema / properties / tools
        Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "additionalProperties": true,
+        "type": "object"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Optional Seedance 2.5 tool configuration objects.",
+  "title": "Tools"
+}
    • Changedseedance_generate_video_from_image10 fields changed
      • changedInput schema / properties / duration / anyOf
        Previous value: -[
-  {
-    "maximum": 15,
-    "minimum": 2,
-    "type": "integer"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "maximum": 30,
+    "minimum": -1,
+    "type": "integer"
+  },
+  {
+    "type": "null"
+  }
+]
      • changedInput schema / properties / duration / description
        Previous value: -"Video duration in seconds. Range: 2-15 (Seedance 2.0 supports 4-15). Default is 5. Mutually exclusive with 'frames'."New value: +"Video duration in seconds. 1.0 series: 2–12; 1.5 Pro: 4–12; 2.0 series: 4–15; 2.5: 4–30. Use -1 for auto-duration (1.5 Pro and 2.x). Default is 5. Mutually exclusive with 'frames'."
      • changedInput schema / properties / frames / anyOf
        Previous value: -[
-  {
-    "type": "integer"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "maximum": 289,
+    "minimum": 29,
+    "type": "integer"
+  },
+  {
+    "type": "null"
+  }
+]
      • changedInput schema / properties / frames / description
        Previous value: -"Frame count for the generated video. Must satisfy 25+4n (e.g. 29, 33, 37, ..., 361). Mutually exclusive with 'duration'."New value: +"Frame count for the generated video (1.0 series only). Must satisfy 25+4n (e.g. 29, 33, 37, ..., 289). Mutually exclusive with 'duration'."
      • changedInput schema / properties / generate_audio / description
        Previous value: -"If true, generate audio. Supported by 'doubao-seedance-1-5-pro-251215' and the 'doubao-seedance-2-0' series. Default is false."New value: +"If true, generate audio. Supported by 'doubao-seedance-1-5-pro-251215' and the Seedance 2.x series. Default is false."
      • changedInput schema / properties / model / enum
        Previous value: -[
-  "doubao-seedance-2-0-260128",
-  "doubao-seedance-2-0-fast-260128",
-  "doubao-seedance-2-0-mini-260615",
-  "doubao-seedance-1-5-pro-251215",
-  "doubao-seedance-1-0-pro-250528",
-  "doubao-seedance-1-0-pro-fast-251015",
-  "doubao-seedance-1-0-lite-t2v-250428",
-  "doubao-seedance-1-0-lite-i2v-250428"
-]New value: +[
+  "doubao-seedance-2-5-260628",
+  "doubao-seedance-2-0-260128",
+  "doubao-seedance-2-0-fast-260128",
+  "doubao-seedance-2-0-mini-260615",
+  "doubao-seedance-1-5-pro-251215",
+  "doubao-seedance-1-0-pro-250528",
+  "doubao-seedance-1-0-pro-fast-251015",
+  "doubao-seedance-1-0-lite-t2v-250428",
+  "doubao-seedance-1-0-lite-i2v-250428"
+]
      • addedInput schema / properties / omni_reference_task_type
        Added value: +{
+  "anyOf": [
+    {
+      "enum": [
+        "auto",
+        "edit",
+        "extend"
+      ],
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Seedance 2.5 task type: auto, edit, or extend.",
+  "title": "Omni Reference Task Type"
+}
      • addedInput schema / properties / output_format
        Added value: +{
+  "anyOf": [
+    {
+      "enum": [
+        "mp4",
+        "mov"
+      ],
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Seedance 2.5 output format: mp4 or mov.",
+  "title": "Output Format"
+}
      • removedInput schema / properties / service_tier
        Removed value: -{
-  "default": "default",
-  "description": "Service tier. 'default' or 'flex' (50%% cheaper). Default is 'default'.",
-  "enum": [
-    "default",
-    "flex"
-  ],
-  "title": "Service Tier",
-  "type": "string"
-}
      • addedInput schema / properties / tools
        Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "additionalProperties": true,
+        "type": "object"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Optional Seedance 2.5 tool configuration objects.",
+  "title": "Tools"
+}
  5. 2 tool updatesv0.1.7
    • Changedseedance_generate_video9 fields changed
      • changedInput schema / properties / duration / anyOf
        Previous value: -[
-  {
-    "maximum": 12,
-    "minimum": 2,
-    "type": "integer"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "maximum": 15,
+    "minimum": 2,
+    "type": "integer"
+  },
+  {
+    "type": "null"
+  }
+]
      • changedInput schema / properties / duration / description
        Previous value: -"Video duration in seconds. Range: 2-12. Default is 5. Mutually exclusive with 'frames'."New value: +"Video duration in seconds. Range: 2-15 (Seedance 2.0 supports 4-15). Default is 5. Mutually exclusive with 'frames'."
      • changedInput schema / properties / frames / description
        Previous value: -"Frame count for the generated video. Must satisfy 25+4n (e.g. 29, 33, 37, ..., 289). Mutually exclusive with 'duration'."New value: +"Frame count for the generated video. Must satisfy 25+4n (e.g. 29, 33, 37, ..., 361). Mutually exclusive with 'duration'."
      • changedInput schema / properties / generate_audio / description
        Previous value: -"If true, generate audio along with the video. Only supported by 'doubao-seedance-1-5-pro-251215' model. Approximately doubles the cost. Default is false."New value: +"If true, generate audio along with the video. Supported by 'doubao-seedance-1-5-pro-251215' and the 'doubao-seedance-2-0' series; other models ignore it. Approximately doubles the cost. Default is false."
      • changedInput schema / properties / model / default
        Previous value: -"doubao-seedance-1-0-pro-250528"New value: +"doubao-seedance-2-0-260128"
      • changedInput schema / properties / model / description
        Previous value: -"Model version to use. Options: 'doubao-seedance-2-0-260128' (latest generation quality model), 'doubao-seedance-2-0-fast-260128' (latest generation fast model), 'doubao-seedance-1-5-pro-251215' (newest flagship, supports audio), 'doubao-seedance-1-0-pro-250528' (standard, default), 'doubao-seedance-1-0-pro-fast-251015' (fast, cost-optimized), 'doubao-seedance-1-0-lite-t2v-250428' (lightweight text-to-video), 'doubao-seedance-1-0-lite-i2v-250428' (lightweight image-to-video)."New value: +"Model version to use. Options: 'doubao-seedance-2-0-260128' (latest generation, highest quality, supports 4k and multimodal reference, default), 'doubao-seedance-2-0-fast-260128' (latest generation, faster, up to 720p), 'doubao-seedance-2-0-mini-260615' (latest generation, lightweight, cheapest within the 2.0 series, up to 720p), 'doubao-seedance-1-5-pro-251215' (1.5 flagship, supports audio), 'doubao-seedance-1-0-pro-250528' (1.0 standard), 'doubao-seedance-1-0-pro-fast-251015' (1.0 fast, cost-optimized), 'doubao-seedance-1-0-lite-t2v-250428' (lightweight text-to-video), 'doubao-seedance-1-0-lite-i2v-250428' (lightweight image-to-video)."
      • changedInput schema / properties / model / enum
        Previous value: -[
-  "doubao-seedance-1-5-pro-251215",
-  "doubao-seedance-1-0-pro-250528",
-  "doubao-seedance-1-0-pro-fast-251015",
-  "doubao-seedance-1-0-lite-t2v-250428",
-  "doubao-seedance-1-0-lite-i2v-250428",
-  "doubao-seedance-2-0-260128",
-  "doubao-seedance-2-0-fast-260128"
-]New value: +[
+  "doubao-seedance-2-0-260128",
+  "doubao-seedance-2-0-fast-260128",
+  "doubao-seedance-2-0-mini-260615",
+  "doubao-seedance-1-5-pro-251215",
+  "doubao-seedance-1-0-pro-250528",
+  "doubao-seedance-1-0-pro-fast-251015",
+  "doubao-seedance-1-0-lite-t2v-250428",
+  "doubao-seedance-1-0-lite-i2v-250428"
+]
      • changedInput schema / properties / resolution / description
        Previous value: -"Video resolution. Options: '480p', '720p' (default), '1080p'."New value: +"Video resolution. Options: '480p', '720p' (default), '1080p', '4k'. '4k' is supported only by 'doubao-seedance-2-0-260128'; '2-0-fast' and '2-0-mini' max out at '720p'."
      • changedInput schema / properties / resolution / enum
        Previous value: -[
-  "480p",
-  "720p",
-  "1080p"
-]New value: +[
+  "480p",
+  "720p",
+  "1080p",
+  "4k"
+]
    • Changedseedance_generate_video_from_image12 fields changed
      • changedInput schema / properties / duration / anyOf
        Previous value: -[
-  {
-    "maximum": 12,
-    "minimum": 2,
-    "type": "integer"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "maximum": 15,
+    "minimum": 2,
+    "type": "integer"
+  },
+  {
+    "type": "null"
+  }
+]
      • changedInput schema / properties / duration / description
        Previous value: -"Video duration in seconds. Range: 2-12. Default is 5. Mutually exclusive with 'frames'."New value: +"Video duration in seconds. Range: 2-15 (Seedance 2.0 supports 4-15). Default is 5. Mutually exclusive with 'frames'."
      • changedInput schema / properties / frames / description
        Previous value: -"Frame count for the generated video. Must satisfy 25+4n (e.g. 29, 33, 37, ..., 289). Mutually exclusive with 'duration'."New value: +"Frame count for the generated video. Must satisfy 25+4n (e.g. 29, 33, 37, ..., 361). Mutually exclusive with 'duration'."
      • changedInput schema / properties / generate_audio / description
        Previous value: -"If true, generate audio. Only supported by 1.5 Pro model. Default is false."New value: +"If true, generate audio. Supported by 'doubao-seedance-1-5-pro-251215' and the 'doubao-seedance-2-0' series. Default is false."
      • changedInput schema / properties / model / default
        Previous value: -"doubao-seedance-1-0-pro-250528"New value: +"doubao-seedance-2-0-260128"
      • changedInput schema / properties / model / description
        Previous value: -"Model version to use. Use 'doubao-seedance-2-0-260128' for latest generation quality, 'doubao-seedance-2-0-fast-260128' for latest generation speed, For image-to-video, consider 'doubao-seedance-1-0-lite-i2v-250428' for lightweight I2V, or any Pro model for higher quality."New value: +"Model version to use. Use 'doubao-seedance-2-0-260128' (default) for latest-generation quality and multimodal reference, 'doubao-seedance-2-0-fast-260128' or 'doubao-seedance-2-0-mini-260615' for faster/cheaper 2.0, or a 1.x model such as 'doubao-seedance-1-0-lite-i2v-250428' for lightweight I2V."
      • changedInput schema / properties / model / enum
        Previous value: -[
-  "doubao-seedance-1-5-pro-251215",
-  "doubao-seedance-1-0-pro-250528",
-  "doubao-seedance-1-0-pro-fast-251015",
-  "doubao-seedance-1-0-lite-t2v-250428",
-  "doubao-seedance-1-0-lite-i2v-250428",
-  "doubao-seedance-2-0-260128",
-  "doubao-seedance-2-0-fast-260128"
-]New value: +[
+  "doubao-seedance-2-0-260128",
+  "doubao-seedance-2-0-fast-260128",
+  "doubao-seedance-2-0-mini-260615",
+  "doubao-seedance-1-5-pro-251215",
+  "doubao-seedance-1-0-pro-250528",
+  "doubao-seedance-1-0-pro-fast-251015",
+  "doubao-seedance-1-0-lite-t2v-250428",
+  "doubao-seedance-1-0-lite-i2v-250428"
+]
      • addedInput schema / properties / reference_audio_urls
        Added value: +{
+  "default": [],
+  "description": "Seedance 2.0 only. Reference audio URLs (up to 3) for voice timbre / background music. Ignored by 1.x models.",
+  "items": {
+    "type": "string"
+  },
+  "title": "Reference Audio Urls",
+  "type": "array"
+}
      • changedInput schema / properties / reference_image_urls / description
        Previous value: -"List of reference image URLs for style/content guidance. These images influence the look but are not used as frames. Cannot be combined with first_frame_url or last_frame_url."New value: +"List of reference image URLs for style/content guidance. For the Seedance 2.0 series these can be real-person / character references that keep the subject consistent (up to 9). These images influence the look but are not used as frames. Cannot be combined with first_frame_url or last_frame_url."
      • addedInput schema / properties / reference_video_urls
        Added value: +{
+  "default": [],
+  "description": "Seedance 2.0 only. Reference video URLs (up to 3) for subject, camera movement, motion or overall style. Ignored by 1.x models.",
+  "items": {
+    "type": "string"
+  },
+  "title": "Reference Video Urls",
+  "type": "array"
+}
      • changedInput schema / properties / resolution / description
        Previous value: -"Video resolution. Options: '480p', '720p', '1080p'."New value: +"Video resolution. Options: '480p', '720p', '1080p', '4k'. '4k' is supported only by 'doubao-seedance-2-0-260128'; '2-0-fast' and '2-0-mini' max out at '720p'."
      • changedInput schema / properties / resolution / enum
        Previous value: -[
-  "480p",
-  "720p",
-  "1080p"
-]New value: +[
+  "480p",
+  "720p",
+  "1080p",
+  "4k"
+]
  6. 7 tool updatesv0.1.5
    • Addedseedance_generate_video
    • Addedseedance_generate_video_from_image
    • Addedseedance_get_task
    • Addedseedance_get_tasks_batch
    • Addedseedance_list_actions
    • Addedseedance_list_models
    • Addedseedance_list_resolutions
  7. 7 tool updatesv0.1.3
    • Removedseedance_generate_video
    • Removedseedance_generate_video_from_image
    • Removedseedance_get_task
    • Removedseedance_get_tasks_batch
    • Removedseedance_list_actions
    • Removedseedance_list_models
    • Removedseedance_list_resolutions
  8. 2 tool updatesv0.1.1
    • Changedseedance_generate_video2 fields changed
      • changedInput schema / properties / model / description
        Previous value: -"Model version to use. Options: 'doubao-seedance-1-5-pro-251215' (newest flagship, supports audio), 'doubao-seedance-1-0-pro-250528' (standard, default), 'doubao-seedance-1-0-pro-fast-251015' (fast, cost-optimized), 'doubao-seedance-1-0-lite-t2v-250428' (lightweight text-to-video), 'doubao-seedance-1-0-lite-i2v-250428' (lightweight image-to-video)."New value: +"Model version to use. Options: 'doubao-seedance-2-0-260128' (latest generation quality model), 'doubao-seedance-2-0-fast-260128' (latest generation fast model), 'doubao-seedance-1-5-pro-251215' (newest flagship, supports audio), 'doubao-seedance-1-0-pro-250528' (standard, default), 'doubao-seedance-1-0-pro-fast-251015' (fast, cost-optimized), 'doubao-seedance-1-0-lite-t2v-250428' (lightweight text-to-video), 'doubao-seedance-1-0-lite-i2v-250428' (lightweight image-to-video)."
      • changedInput schema / properties / model / enum
        Previous value: -[
-  "doubao-seedance-1-5-pro-251215",
-  "doubao-seedance-1-0-pro-250528",
-  "doubao-seedance-1-0-pro-fast-251015",
-  "doubao-seedance-1-0-lite-t2v-250428",
-  "doubao-seedance-1-0-lite-i2v-250428"
-]New value: +[
+  "doubao-seedance-1-5-pro-251215",
+  "doubao-seedance-1-0-pro-250528",
+  "doubao-seedance-1-0-pro-fast-251015",
+  "doubao-seedance-1-0-lite-t2v-250428",
+  "doubao-seedance-1-0-lite-i2v-250428",
+  "doubao-seedance-2-0-260128",
+  "doubao-seedance-2-0-fast-260128"
+]
    • Changedseedance_generate_video_from_image2 fields changed
      • changedInput schema / properties / model / description
        Previous value: -"Model version to use. For image-to-video, consider 'doubao-seedance-1-0-lite-i2v-250428' for lightweight I2V, or any Pro model for higher quality."New value: +"Model version to use. Use 'doubao-seedance-2-0-260128' for latest generation quality, 'doubao-seedance-2-0-fast-260128' for latest generation speed, For image-to-video, consider 'doubao-seedance-1-0-lite-i2v-250428' for lightweight I2V, or any Pro model for higher quality."
      • changedInput schema / properties / model / enum
        Previous value: -[
-  "doubao-seedance-1-5-pro-251215",
-  "doubao-seedance-1-0-pro-250528",
-  "doubao-seedance-1-0-pro-fast-251015",
-  "doubao-seedance-1-0-lite-t2v-250428",
-  "doubao-seedance-1-0-lite-i2v-250428"
-]New value: +[
+  "doubao-seedance-1-5-pro-251215",
+  "doubao-seedance-1-0-pro-250528",
+  "doubao-seedance-1-0-pro-fast-251015",
+  "doubao-seedance-1-0-lite-t2v-250428",
+  "doubao-seedance-1-0-lite-i2v-250428",
+  "doubao-seedance-2-0-260128",
+  "doubao-seedance-2-0-fast-260128"
+]
  9. 7 tool updatesv0.1.0
    • First observedseedance_generate_video
    • First observedseedance_generate_video_from_image
    • First observedseedance_get_task
    • First observedseedance_get_tasks_batch
    • First observedseedance_list_actions
    • First observedseedance_list_models
    • First observedseedance_list_resolutions
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.4/5.0

Scored across 7 tools

Disambiguation5/5

Each tool serves a clearly distinct purpose: listing models, listing resolutions, listing actions, querying a single task, querying multiple tasks, generating from text, and generating from images. There is no overlap or ambiguity in tool boundaries.

Naming Consistency5/5

All tools follow a consistent seedance_ prefix with snake_case verb_noun naming (e.g., seedance_list_models, seedance_generate_video_from_image). The pattern is uniform and predictable across the entire set.

Tool Count5/5

With 7 tools, the set is well-scoped for a video generation API: three discovery tools, two status-query tools, and two generation methods. Each tool earns its place without redundancy or bloat.

Completeness5/5

The server covers the full video-generation workflow: model and resolution discovery, two generation modes, and both single and batch status retrieval. No essential operations (e.g., cancel, delete) seem necessary for the domain, and the existing tools provide all needed functionality.

Maintenance

ActivityActive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers