Skip to main content
Glama
deenesjakoruzh
leonaiuv

seedance-2-mcp

by leonaiuv
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

seedance-2-mcp

npm version License: MIT

一个开源、本地运行的 MCP (Model Context Protocol) 服务器，把火山方舟 (Volcengine ARK) Seedance 2.0 视频生成能力以三个 stdio 工具的形式暴露给 Codex、Claude Desktop、Cursor 等任意 MCP 客户端。

  • 纯本地 stdio，不需要任何云端部署。

  • 由 Node.js + TypeScript 编写，使用官方 @modelcontextprotocol/sdk。

  • 用户在自己机器上配置 ARK_API_KEY 即可调用 Seedance 2.0 的 文生视频 / 图生视频 / 多模态参考生成。

提供的 MCP Tools

Tool

作用

seedance_usage_guide

返回完整的使用说明 — 标准流程、模型选择、参数表、注意事项。

seedance_create_task

提交一个 Seedance 2.0 视频生成任务，立即返回 task_id，不阻塞。

seedance_check_task

用 task_id 查询任务状态，成功后返回 video_url 和可选末帧图片。

详细参数见 Tools 详解。

Related MCP server: Seedance MCP

给本地 Agent 的快速接入提示词

如果你正在使用 Codex、Claude Desktop、Cursor 或其他支持 MCP 的本地 Agent，可以直接把本仓库链接发给它，并让它阅读这一段。

你是一个本地开发 Agent。请帮我把这个仓库提供的 seedance-2-mcp 接入到当前 MCP 客户端中。

目标：
1. 读取仓库 README，理解这是一个 stdio MCP server，用于调用火山方舟 Seedance 2.0 视频生成 API。
2. 优先使用 npx 方式接入：command = "npx"，args = ["-y", "seedance-2-mcp"]。
3. 如果 npm 包暂不可用，或我明确想从源码运行，请 clone 本仓库，执行 npm install && npm run build，并将 MCP command 配为 "node"，args 配为 ["<仓库绝对路径>/dist/index.js"]。
4. 只向我索要或确认 ARK_API_KEY，不要把真实 API Key 写进仓库、README、示例文件或 git。
5. 根据我当前使用的客户端自动修改对应 MCP 配置：
   - Codex：修改 ~/.codex/config.toml
   - Claude Desktop：修改 claude_desktop_config.json
   - Cursor 或其他客户端：使用它们支持的 stdio MCP 配置格式
6. 配置完成后，提醒我重启或刷新 MCP 客户端，然后先调用 seedance_usage_guide，再按 create -> wait -> check 的流程生成视频。
7. 如果本机没有 Node.js >= 18 或 npx 不可用，请先指出缺失项，并给出最小安装建议。

重要约束：
- stdout 是 MCP JSON-RPC 通道，不要让 server 在 stdout 打调试日志。
- ARK_API_KEY 只能放在 MCP 客户端 env 配置或本机环境变量里。
- 生成的 video_url 通常会过期，任务成功后应提示我尽快下载。

你也可以直接对 Agent 说：

阅读这个仓库并按 README 里的“给本地 Agent 的快速接入提示词”帮我配置 Seedance MCP。我会提供 ARK_API_KEY。

安装

1. 通过 npx（推荐 - 无需手动安装）

MCP 客户端的配置里直接用：

npx -y seedance-2-mcp

每次启动会下载（或复用缓存）最新版本。

2. 全局安装

npm install -g seedance-2-mcp

之后在客户端配置里使用 seedance-2-mcp 即可。

3. 从源码运行（开发者）

git clone https://github.com/seedance/seedance-2-mcp.git
cd seedance-2-mcp
npm install
npm run build
node dist/index.js

要求 Node.js >= 18（依赖原生 fetch）。

环境变量

变量

必填

说明

ARK_API_KEY

是

火山方舟 API Key。前往 https://console.volcengine.com/ark 获取。

ARK_BASE_URL

否

默认 https://ark.cn-beijing.volces.com/api/v3。海外/代理可覆盖。

复制 .env.example 到本地 .env 仅作开发参考；真正生效的位置是 MCP 客户端配置里的 env， 因为客户端通过子进程拉起 MCP，会自己注入环境变量。

如果工具调用时未设置 ARK_API_KEY，三个工具中调用真实 API 的两个都会返回清晰错误：

Missing ARK_API_KEY environment variable. Please set ARK_API_KEY to your Volcengine ARK API key.

客户端配置示例

Codex（~/.codex/config.toml）

[mcp_servers.seedance-2-mcp]
command = "npx"
args = ["-y", "seedance-2-mcp"]
env = { "ARK_API_KEY" = "your_key_here" }

Claude Desktop（claude_desktop_config.json）

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

{
  "mcpServers": {
    "seedance-2-mcp": {
      "command": "npx",
      "args": ["-y", "seedance-2-mcp"],
      "env": {
        "ARK_API_KEY": "your_key_here"
      }
    }
  }
}

Cursor / 其他 MCP 客户端

任何支持 stdio MCP 的客户端通用配置：

{
  "command": "npx",
  "args": ["-y", "seedance-2-mcp"],
  "env": { "ARK_API_KEY": "your_key_here" }
}

Tools 详解

seedance_usage_guide

无参数。返回 Markdown 格式的完整使用说明。建议在首次调用 seedance_create_task 之前先调用一次。

seedance_create_task

提交一个视频生成任务，立即返回 task_id。

输入参数：

字段

类型

默认

说明

prompt

string

—（必填）

自然语言描述。如有参考素材，在 prompt 中用 [Image1] / [Video1] / [Audio1] 引用。

model

enum

doubao-seedance-2-0-260128

doubao-seedance-2-0-260128（标准版，最高质量）/ doubao-seedance-2-0-fast-260128（快速版）。

duration

integer

5

视频时长，单位秒。[4, 15]。

ratio

enum

16:9

21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16 / adaptive。

resolution

enum

720p

480p 或 720p。

generate_audio

boolean

true

是否同时生成同步音频（对白 / 音效 / BGM）。

watermark

boolean

true

是否添加平台水印。部分账号可能无法关闭。

web_search

boolean

false

是否对 prompt 启用联网增强；仅纯文本输入可用，不能与 image/video/audio 同时使用。

return_last_frame

boolean

false

是否返回末帧图片 URL，用于多段拼接。

image_urls

array

—

最多 9 项；每项 { url, role? }，role ∈ reference_image / first_frame / last_frame，默认 reference_image。

video_urls

array

—

最多 3 项；每项 { url, role? }，role ∈ reference_video。

audio_urls

array

—

最多 3 项；每项 { url, role? }，role ∈ reference_audio。必须配合 image 或 video。

校验规则：

  • duration 必须是 [4, 15] 之间的整数。

  • image_urls ≤ 9，video_urls ≤ 3，audio_urls ≤ 3。

  • 仅纯文本 + audio_urls 会被拒绝（Seedance 不支持）。

  • web_search=true 与任何参考素材同时出现会被拒绝（联网增强只支持纯文本）。

返回：

{
  "task_id": "cgt-2026xxxx-xxxxxx",
  "model": "doubao-seedance-2-0-260128",
  "duration": 5,
  "ratio": "16:9",
  "resolution": "720p",
  "raw": { /* 火山原始响应 */ }
}

seedance_check_task

输入 { task_id: string }。可能的状态：

  • running / queued / pending — 仍在处理。提示等待 30-90 秒后再调用。

  • succeeded — 返回 video_url，若 return_last_frame=true 也会返回 last_frame_url。

  • failed — 返回 fail_reason（如有）。

  • cancelled / expired — 任务已取消或已过期。

  • 其他 — 原样回传 status 与原始 payload。

典型调用流程

client → seedance_usage_guide                                  ← 阅读规则
client → seedance_create_task { prompt, ... }                  ← 提交任务
                                                ↓
                                        task_id: cgt-...
                                                ↓
client → seedance_check_task { task_id }                       ← 30-90s 后轮询
                                ↓
                        status: running         （继续等待）
                                ↓
                        status: succeeded       ← 返回 video_url
                                ↓
                立刻下载 video_url（约 24h 内会过期）

15 秒标准模型任务通常需要 2-5 分钟完成；快速版会更短。

安全说明

  • 不要把 ARK_API_KEY 写进 git 仓库。把它放在 MCP 客户端配置（如 claude_desktop_config.json、~/.codex/config.toml）的 env 字段，或者 shell 环境变量里。

  • 本工具不会在日志或返回值里打印 ARK_API_KEY。

  • 火山生成的 video_url 和 last_frame_url 是带签名的临时 URL，根据火山官方说明默认 24 小时内有效；任务成功后请尽快下载，避免链接过期。

  • 你传入的 image_urls / video_urls / audio_urls 都需要 公网可访问 的 HTTPS（或 HTTP）地址；本地路径、内网地址、需要登录的资源无法被火山服务器拉取。

  • 请遵守火山方舟与 Seedance 模型的使用条款，不要生成违法、未成年人不当或侵权内容。

开发

npm install
npm run typecheck
npm run dev          # 用 tsx 直接跑 src/index.ts
npm run build        # 输出到 dist/
npm start            # node dist/index.js

调试 stdio MCP 推荐：

npx -y @modelcontextprotocol/inspector npx -y seedance-2-mcp

或本地源码：

npx -y @modelcontextprotocol/inspector node dist/index.js

项目结构

.
├── src/
│   ├── index.ts          # stdio MCP 入口（带 shebang）
│   ├── server.ts         # 注册 McpServer 和三个 tools
│   ├── seedance.ts       # 火山方舟 Seedance 2.0 REST API 客户端
│   ├── schema.ts         # zod 输入 schema
│   └── usageGuide.ts     # seedance_usage_guide 返回的文本
├── package.json
├── tsconfig.json
├── .env.example
├── .gitignore
├── LICENSE
└── README.md

协议

MIT © seedance-2-mcp contributors

本项目与字节跳动、火山引擎、Volcengine ARK 均无官方关联。 "Seedance"、"Doubao"、"火山方舟" 等名称版权归各自持有人所有。

Available Tools

3 tools
seedance_check_taskCheck Seedance 2.0 task statusA
Read-onlyIdempotent

Query the status of a Seedance 2.0 task by task_id. Returns running / succeeded / failed / other. On success returns video_url (and last_frame_url if return_last_frame was true). Generated URLs expire within ~24h - download promptly.

ParametersJSON Schema
NameRequiredDescriptionDefault
task_idYesSeedance task id returned by seedance_create_task (e.g. cgt-...).

TDQS

A4.2/5.0
Behavior4/5

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

Annotations indicate readOnly and idempotent. Description adds URL expiration (~24h) and return format, which isn't in annotations. No contradiction.

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?

Three sentences, front-loaded with purpose, no redundant or extraneous content. Efficient and clear.

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?

Describes statuses and URL expiry without output schema. Adequate for a status check tool; could mention error handling but not required.

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 has 100% coverage with description for task_id. Description adds context that it's the ID from seedance_create_task, improving usability.

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 queries status of a Seedance 2.0 task by task_id, lists possible statuses and success returns. Distinguishes from sibling tools (create and guide).

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?

Implies usage after task creation but does not explicitly state when to use vs alternatives or mention polling patterns. No when-not or alternatives provided.

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

seedance_create_taskCreate Seedance 2.0 video generation taskA

Submit a Seedance 2.0 video generation task to the Volcengine ARK API and return the task_id immediately. Does NOT wait for the video to render - poll seedance_check_task afterwards. Reference media URLs must be publicly reachable.

ParametersJSON Schema
NameRequiredDescriptionDefault
promptYesNatural-language description of the desired video. Reference images / videos / audios with [Image1], [Video1], [Audio1] in 1-based order if you provided any.
modelNoSeedance 2.0 model id. doubao-seedance-2-0-260128 is the standard, highest-quality model. doubao-seedance-2-0-fast-260128 trades quality for latency.doubao-seedance-2-0-260128
durationNoVideo length in seconds. Must be an integer in [4, 15].
ratioNoAspect ratio. Use 9:16 for vertical short-video, 16:9 for landscape. 'adaptive' lets the model pick the best fit when reference media is provided.16:9
resolutionNoOutput resolution. 720p is recommended; 480p is faster/cheaper.720p
generate_audioNoWhether to generate synchronized audio (dialogue, SFX, music). Set false for silent video.
watermarkNoWhether to add the platform watermark. Some accounts cannot disable this.
web_searchNoEnable prompt enhancement via web search. Text-only input is required when this is true.
return_last_frameNoReturn the last frame as an image URL alongside the video URL. Useful for chaining segments.
image_urlsNoUp to 9 reference images. Each item is { url, role? }. role defaults to 'reference_image'. Use 'first_frame' (and optionally 'last_frame') for image-to-video animation.
video_urlsNoUp to 3 reference videos. Each item is { url, role? }. role defaults to 'reference_video'.
audio_urlsNoUp to 3 reference audios. Each item is { url, role? }. role defaults to 'reference_audio'. Audio MUST be paired with at least one image or video reference.

TDQS

A4.6/5.0
Behavior4/5

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

Annotations indicate readOnlyHint=false, and the description confirms a mutation (creates a task). It adds context beyond annotations: the async nature ('Does NOT wait for the video to render') and the requirement for public URLs. However, it does not mention rate limits, error handling, or response structure.

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?

Three sentences containing no fluff: first states core function, second explains async behavior with action, third adds constraint. Front-loaded with the most important information.

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?

For a tool with 12 parameters and no output schema, the description covers the essential workflow and a key constraint (public URLs). It lacks details on error cases or the exact format of the returned task_id, but the async instruction is clear. Overall adequate but could be slightly more detailed.

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 is 100%, so baseline is 3. The description adds value beyond schema by emphasizing the async behavior and public URL requirement, which are not evident from individual parameter descriptions. It also clarifies the workflow (submit then poll).

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 the verb 'Submit' and the resource 'Seedance 2.0 video generation task'. It specifies that it returns a task_id immediately and does not wait for rendering, distinguishing it from sibling tools like seedance_check_task that are used for polling.

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 explicitly instructs to poll seedance_check_task afterwards and notes that reference media URLs must be publicly reachable. It provides clear guidance on when to use this tool (to initiate a task) and what to do next (poll for results).

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

seedance_usage_guideSeedance 2.0 usage guideA
Read-onlyIdempotent

Returns the canonical usage guide for the Seedance 2.0 MCP: standard create -> wait -> check workflow, model choices, parameter reference, and important caveats. Call this before your first seedance_create_task.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A4.3/5.0
Behavior3/5

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

Annotations (readOnlyHint, idempotentHint) already declare safe, idempotent behavior. The description adds that it returns a guide, but no additional behavioral traits beyond what annotations provide.

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?

Two sentences, no wasted words. Front-loaded with key purpose and usage instruction. Highly concise and well-structured.

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?

For a zero-parameter, no-output-schema guide tool, the description fully explains its purpose, content, and when to use it. No 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 exist, so baseline is 4. The description adds meaning by explaining the tool's purpose and content, compensating for lack of parameters.

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 it returns the canonical usage guide for Seedance 2.0 MCP, detailing workflow, model choices, parameters, and caveats. It distinguishes itself from sibling tools (check, create) by being the preliminary guide.

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 advice to call before first seedance_create_task provides clear context for use. No exclusions or alternatives are needed given its unique role as a guide.

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. 3 tool updatesv0.1.0
    • First observedseedance_check_task
    • First observedseedance_create_task
    • First observedseedance_usage_guide
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 3 tools

Disambiguation5/5

Each tool has a unique and clear purpose: creating a task, checking its status, and providing usage instructions. There is no overlap in functionality.

Naming Consistency4/5

All tools share the 'seedance_' prefix and follow a noun-based pattern (check_task, create_task, usage_guide), but 'usage_guide' is not a verb_noun like the others, causing minor inconsistency.

Tool Count5/5

With only 3 tools, the set is tightly scoped to the core workflow of generating and monitoring a video task, plus a guide. This is appropriate for the narrow domain.

Completeness4/5

The tools cover the essential create-and-check workflow, and the guide complements them. However, missing operations like task cancellation or listing are minor gaps but not critical for the basic use case.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers