Seedance Polza MCP Server
Provides integration with ByteDance's Seedance video generation models (e.g., seedance-2) via the Polza.ai API, enabling text-to-video and image-to-video generation, status polling, and retrieval of generated video URLs.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Seedance Polza MCP Server make a 5-second video of a sunset over the ocean"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Seedance Polza MCP Server
mcp-name: io.github.ivanantigravity-lgtm/seedance-polza-mcp-server
MCP сервер для генерации видео через bytedance/seedance-2 (и другие Seedance-модели) на Polza.ai.
Что умеет
text-to-video и image-to-video генерация
чтение статуса генерации
polling до готовности видео
возвращает компактный результат (id, статус, url, usage, warnings)
Related MCP server: Seedance MCP
Что нужно для установки
Claude DesktopилиClaude CodePython 3.11+
POLZA_AI_API_KEY— ключ берётся на polza.ai/dashboard/api-keys
Поставить uv:
curl -LsSf https://astral.sh/uv/install.sh | shУстановка за 2 минуты (через PyPI + uvx)
Claude Code / VS Code
Создай .mcp.json в корне проекта:
{
"mcpServers": {
"seedance-polza": {
"command": "uvx",
"args": ["seedance-polza-mcp-server@latest"],
"env": {
"POLZA_AI_API_KEY": "your-polza-api-key-here"
}
}
}
}Перезапусти Claude Code.
Claude Desktop (macOS)
Файл ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"seedance-polza": {
"command": "uvx",
"args": ["seedance-polza-mcp-server@latest"],
"env": {
"POLZA_AI_API_KEY": "your-polza-api-key-here"
}
}
}
}Claude Desktop (Windows)
Файл: %APPDATA%\Claude\claude_desktop_config.json. Содержимое идентичное.
Как проверить, что работает
После перезапуска Claude попроси:
Сделай через seedance короткое видео: закат над океаном, 16:9, 5 секунд
Claude должен вызвать seedance_create_video и дождаться готовности через seedance_wait_for_completion.
Tools
seedance_create_video— запустить генерациюseedance_get_status— проверить статус поidseedance_wait_for_completion— ждать polling-ом до готовностиseedance_model_guide— краткая памятка по параметрам
Дефолты
модель:
bytedance/seedance-2polling interval:
8секундmax wait:
900секунд
Переменные окружения
Переменная | Обязательная | По умолчанию |
| да | — |
| нет |
|
| нет |
|
| нет |
|
| нет |
|
| нет |
|
Поддерживаемые входные параметры
Базовые параметры под видео:
promptaspect_ratio(16:9,9:16,1:1,4:3,3:4,21:9и т.д.)resolution(480p,720p,1080p)duration(5s,10s,15s— зависит от модели)images— референсы для image-to-videovideos— референсы для video-to-videoseedasyncuser
Формат images / videos:
{ "type": "url", "data": "https://example.com/file.png" }или
{ "type": "base64", "data": "data:image/png;base64,..." }Что возвращает сервер
Сервер не делает лишней магии. Он возвращает:
idгенерацииstatusmodelusage(в том числеcost_rub)urlрезультата, если видео готовоwarnings/errorпри проблемах
Локальная разработка
git clone https://github.com/ivanantigravity-lgtm/seedance-polza-mcp-server.git
cd seedance-polza-mcp-server
uv sync
POLZA_AI_API_KEY=your_key uv run python -m seedance_polza_mcp_server.serverВажно
Этот сервер не гоняет live preview и не тратит токены сам по себе.
Генерация запускается только по явному вызову tool.
Лицензия
MIT.
Available Tools
4 toolsseedance_create_videoC
Create a Seedance video generation through Polza Media API.
Inputs: prompt (required), seed, user, model, +7 more. Returns: result
seedance_get_statusB
Get current status of a media generation by ID.
Inputs: media_id (required). Returns: result
seedance_model_guideA
Return a short practical guide for using Seedance through Polza.
Inputs: no named parameters. Returns: result
seedance_wait_for_completionB
Poll media status until completed, failed, cancelled, or timeout.
Inputs: media_id (required), interval_seconds, max_wait_seconds. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: guide for instructions, create for initiating generation, get_status for one-time status check, and wait_for_completion for polling until done. No overlap or ambiguity between them.
All tool names follow a consistent pattern: 'seedance_' prefix followed by verb_noun (model_guide, create_video, get_status, wait_for_completion). The naming is uniform and predictable.
With only 4 tools, the server is tightly scoped for its purpose of video generation via Seedance. Each tool is essential and there are no redundant or unnecessary additions, making the count appropriate.
The server covers the core lifecycle of video generation: guidance, creation, status checking, and waiting for completion. While a cancel or list operation could be imagined, they are not essential for the primary workflow, so the set is nearly complete.
Maintenance
Related MCP Connectors
Generate Seedance videos with Ace Data Cloud; retrieve the original task for finished video.
AI video and images from a photo or text in ChatGPT and Claude. Seedance 2 Mini by default.
Generate images and videos with Seedance, Veo, Wan, Grok, GPT-Image and Nano Banana via one MCP.
Start a video generation job and poll it until the clip is ready; video price plus $0.01 a call.
Related MCP Servers
- AlicenseAqualityBmaintenanceByteDance Seedance AI video generation with text-to-video, image-to-video, multiple models (1.5 Pro/1.0 Pro/Lite), synchronized audio, and flexible resolutions up to 1080p.7588 PyPI21MIT
- FlicenseAqualityDmaintenanceEnables video generation using the Seedance 2.0 model through MCP, supporting both OpenAI and Volcengine API formats with tools for creating, monitoring, and downloading videos.6-
- FlicenseAqualityDmaintenanceEnables generating videos from images and text prompts using Jimeng Video 3.0 API, supporting 5s/10s durations and automatic result polling.3-
- AlicenseAqualityDmaintenanceEnables video generation from text prompts or images using Agnes AI's video models, with async task submission and status polling.219 npm1MIT