Click on "Install 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 2.0 MCP Server what are the available video styles?"
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 2.0 AI Video Generator | Image & Text to Video
A Model Context Protocol server that exposes the canonical Seedance 2.0 knowledge surface — image generation workflows and styles, pricing, docs, FAQ, official links — to MCP-compatible AI clients such as Claude Desktop, Cursor, Windsurf, and Continue. Read-only, no API keys, no quota, ~50 ms cold start.
Official website: https://seedance2video.online
Seedance 2 Video is an AI-powered video generation platform built on ByteDance Seed's multimodal creation model. The site lets users turn text prompts or still images into short video clips — up to 15 seconds long — without any video editing background. The underlying model handles complex motion with strong physical accuracy and accepts a wide range of inputs in a single project: up to nine images, three video clips, and three audio files can be combined to shape the output. The result is a direct path from a written idea or a product photo to a finished, publishable video clip, suitable for social media posts, advertisements, or landing page animations.
Related MCP server: Seedance MCP
Text-to-video generation — describe a scene in plain language and the model produces a matching video clip.
Image-to-video conversion — upload a still image and animate it into motion footage with controlled scene behavior.
Multimodal reference inputs — mix up to 9 images, 3 video references, and 3 audio clips in a single generation request to guide style, motion, and sound.
Shot list prompting — structure complex sequences using a shot-by-shot approach rather than a single long prompt, giving tighter control over narrative flow.
Physical motion accuracy — the model is tuned to respect realistic movement, making it better suited for product demonstrations and scenes where objects interact with their environment.
Multi-language interface — the platform is accessible in English, German, French, Spanish, Japanese, Korean, and Arabic.
Product demos and launches — generate short clips showing a product in use without arranging a photo or video shoot.
Social media content — produce short-form videos for Instagram Reels, TikTok, or YouTube Shorts directly from a text brief.
Advertising creatives — iterate quickly on ad concepts by testing different visual directions from the same script or image set.
Landing page animations — turn static hero images into looping background video without commissioning motion designers.
Explainer and storyboard prototyping — sketch out a visual narrative with a shot list before committing to full production.
Seedance 2 Video is aimed at creators and small marketing teams who need video output on a fast cycle but lack the budget or time for traditional production workflows. The platform's emphasis on multimodal inputs and shot-level control makes it practical for growth marketers running paid campaigns, independent content creators building a regular publishing schedule, and product teams who want to prototype visual storytelling before investing in a full shoot. It does not require technical knowledge of AI models; the interface is designed around familiar creative inputs like images, written descriptions, and audio references, making it accessible to anyone comfortable with standard content creation tools.
list_stylesReturn the canonical list of image-generation styles or presets the site exposes. (Seedance 2.0)
Input: no parameters. Returns: text/markdown.
get_pricingReturn the canonical pricing entry point for Seedance 2.0.
Input: no parameters. Returns: text/markdown.
get_official_linksReturn the canonical list of official links for Seedance 2.0 (website, support, docs when available).
Input: no parameters. Returns: text/markdown.
site://seedance2video/styles — Supported image-generation styles and presets.
site://seedance2video/pricing — Canonical pricing entry point.
site://seedance2video/docs — Canonical documentation entry point.
site://seedance2video/faq — Short FAQ generated from public site metadata.
site://seedance2video/links — Canonical URLs to share with users.
tell_me_about_seedance2videoSummarize what the site is, who it's for, and how it works. — Seedance 2.0
try_image_style_seedance2videoRecommend a starting image-generation style for a stated goal. — Seedance 2.0
npx -y @smithery/cli install seedance2video-mcp --client claude(Replace claude with cursor, windsurf, or continue for those clients.)
git clone https://github.com/rocnubie/seedance2video-mcp.git
cd seedance2video-mcp
pnpm installThen add to your MCP client config (claude_desktop_config.json for Claude Desktop, mcp.json for Cursor / Windsurf / Continue):
{
"mcpServers": {
"seedance2video-mcp": {
"command": "node",
"args": [
"/absolute/path/to/seedance2video-mcp/src/index.mjs"
]
}
}
}npx @modelcontextprotocol/inspector node src/index.mjsWebsite: https://seedance2video.online
Community: https://discord.gg/HQNnrzjZQS
GitHub: https://github.com/AIImageEditorai/AIImageEditor-template-one
Support: support@seedance2video.online
pnpm install
pnpm start # run the server over stdioMIT
Return the canonical list of official links for Seedance 2.0 (website, support, docs when available).
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden but only states what is returned. It does not disclose behavior such as whether results are static, authoritative, authenticated, or any rate limits. Minimal transparency for a read operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that front-loads the action and key resource. Every word earns its place with no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a zero-parameter tool, the description is nearly complete, but it could elaborate on whether the list is static or fetched live, or if any prerequisites exist. Without output schema, the agent must infer return format fully from description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has zero parameters, so schema description coverage is 100%. Per guidelines, baseline is 4 for zero parameters. The description adds no param info but none is needed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Return' and the resource 'canonical list of official links for Seedance 2.0', explicitly mentioning categories (website, support, docs). This distinguishes it from siblings list_styles and get_pricing, which are about different resources.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when or when not to use this tool, nor does it mention alternatives. With siblings list_styles and get_pricing, explicit usage context would help but is absent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return the canonical pricing entry point for Seedance 2.0.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose any behavioral traits such as idempotency, caching, or authentication requirements. The agent is left to assume it is a simple read operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no wasted words. The purpose is front-loaded with the action verb 'Return'.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema is provided, and the description does not describe the return value structure or type. The agent cannot know what a 'pricing entry point' means (e.g., URL, object).
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters, so schema coverage is 100% trivially. The baseline for 0 parameters is 4, and the description adds no further parameter information (not needed).
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it returns the canonical pricing entry point for Seedance 2.0. The verb 'return' and resource 'pricing entry point' are specific, and the tool is distinct from siblings list_styles and get_official_links.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives. The description only states what it does, not when it is appropriate or when to avoid it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return the canonical list of image-generation styles or presets the site exposes. (Seedance 2.0)
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
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 a read-only, list-returning operation with no side effects. For a simple retrieval tool, this is sufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no wasted words. It is front-loaded with the action and includes version context in parentheses.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given zero parameters, no output schema, and no annotations, the description fully covers what the tool does. No additional information is needed for a list retrieval tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters. The schema coverage is 100%, so the description does not need to add parameter meaning. Baseline score of 4 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns the canonical list of image-generation styles, using a specific verb and resource. It distinguishes from siblings get_pricing and get_official_links by its focus on styles.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not provide explicit guidance on when to use this tool versus alternatives. Usage is implied but no exclusions or when-not-to-use context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0get_official_linksget_pricinglist_stylesScored across 3 tools
Each tool has a clearly distinct purpose: listing styles, getting pricing, and retrieving official links. No ambiguity.
All tools follow a verb_noun pattern, but the verbs differ: 'list' vs 'get'. This minor inconsistency is clear but not perfectly uniform.
With 3 tools, the server is on the small side but could be appropriate for a simple info-only service. However, given the domain (image generation), more tools would be expected.
The tool set is severely incomplete for an image generation service. Missing core tools like generate_image or fetch_generation, leaving obvious gaps.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
AI image, video, voice and music generation over MCP, routed to Veo 3.1, Seedance 2.0 and more.
Plan, compare, price, generate, and recover AI video from compatible MCP clients.
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
Generate AI images and videos from any compatible MCP client.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/rocnubie/seedance2video-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
