Skip to main content
Glama
rocnubie

SeedanceAI MCP Server

by rocnubie
OverviewSchemaSourceRelated ServersScoreDiscussionsAdmin
JavaScript
Remote

SeedanceAI MCP Server

SeedanceAI Video Generator | Image & Text to Video

MCP Badge License: MIT Stdio Transport Zero Config MCP

A Model Context Protocol server that exposes the canonical SeedanceAI 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://seedanceai.online

🎨 About SeedanceAI

Seedance AI is a browser-based video generation platform powered by ByteDance's Seedance 1.0 model. It lets anyone turn a text prompt or a static image into a short, high-quality video without installing any software. The platform supports outputs up to 1080p resolution and produces videos of roughly ten seconds, with natural motion and stable subject structure throughout. A free usage tier is available alongside an optional Pro upgrade, making the tool accessible for quick experimentation as well as more sustained production work. The interface is straightforward: choose a mode, write a prompt or upload an image, pick a style and resolution, and generate.

Related MCP server: Gemini 3 Online MCP Server

Key Features

  • Text-to-video and image-to-video modes — write a description to generate a video from scratch, or animate an existing image while keeping subject structure consistent.

  • Multi-shot narrative generation — produces two to three connected shots with seamless transitions in a single pass, supporting short-form storytelling that single-shot generators cannot match.

  • Four visual styles — realistic, anime, film, and advertisement styles let creators match the output to a specific aesthetic without post-processing.

  • Resolution presets — 480p, 720p, and 1080p options balance generation speed against output quality depending on the use case.

  • Optimized inference pipeline — the backend is tuned for faster generation speeds compared to standard model deployments, reducing wait time between iterations.

  • No-download, account-based access — everything runs in the browser; a sign-in account tracks usage and enables the free tier without local setup.

Use Cases

  • Social media content — creators producing short clips for platforms like Instagram Reels, TikTok, or YouTube Shorts can go from idea to finished video in a few minutes.

  • Storyboarding and concept prototyping — teams can rapidly visualize a scene or ad concept using multi-shot generation before committing to a full production.

  • Animating product images — e-commerce sellers or marketers can bring static product photos to life for ad campaigns using image-to-video mode.

  • Anime and stylized content — the dedicated anime style setting makes it practical for fan creators or studios producing stylized short-form video.

  • Developer and API exploration — solo developers and small teams use the free tier to evaluate the Seedance 1.0 model's capabilities before integrating it into their own pipelines.

Who Is It For

Seedance AI is aimed at content creators, marketers, and developers who need fast video output without a steep learning curve or expensive tooling. Creators who regularly produce short-form video for social platforms will find the multi-shot and style options directly useful. Marketers and product teams benefit from the image-to-video path, which lets them repurpose existing assets quickly. Developers evaluating ByteDance's Seedance 1.0 model get a hands-on interface to test capabilities before building integrations. The free tier lowers the barrier for individuals and small teams, while the Pro upgrade serves users who need higher throughput or priority access.

Tools

list_styles

Return the canonical list of image-generation styles or presets the site exposes. (SeedanceAI)

Input: no parameters. Returns: text/markdown.

get_pricing

Return the canonical pricing entry point for SeedanceAI.

Input: no parameters. Returns: text/markdown.

get_official_links

Return the canonical list of official links for SeedanceAI (website, support, docs when available).

Input: no parameters. Returns: text/markdown.

Resources

  • site://seedanceai/styles — Supported image-generation styles and presets.

  • site://seedanceai/pricing — Canonical pricing entry point.

  • site://seedanceai/docs — Canonical documentation entry point.

  • site://seedanceai/faq — Short FAQ generated from public site metadata.

  • site://seedanceai/links — Canonical URLs to share with users.

Prompts

tell_me_about_seedanceai

Summarize what the site is, who it's for, and how it works. — SeedanceAI

try_image_style_seedanceai

Recommend a starting image-generation style for a stated goal. — SeedanceAI

Installation

Install via Smithery

npx -y @smithery/cli install seedanceai-mcp --client claude

(Replace claude with cursor, windsurf, or continue for those clients.)

Install from source

git clone https://github.com/rocnubie/seedanceai-mcp.git
cd seedanceai-mcp
pnpm install

Then add to your MCP client config (claude_desktop_config.json for Claude Desktop, mcp.json for Cursor / Windsurf / Continue):

{
  "mcpServers": {
    "seedanceai-mcp": {
      "command": "node",
      "args": [
        "/absolute/path/to/seedanceai-mcp/src/index.mjs"
      ]
    }
  }
}

Debug with MCP Inspector

npx @modelcontextprotocol/inspector node src/index.mjs

Official Links

Development

pnpm install
pnpm start                 # run the server over stdio

License

MIT

Available Tools

3 tools
get_pricingA

Return the canonical pricing entry point for SeedanceAI.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A3.5/5.0
Behavior2/5

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

No annotations are provided, so the description carries full burden. It only states the tool returns the pricing entry point, but does not disclose any behavioral traits such as whether it is read-only, requires authentication, or has rate limits. This is insufficient for a tool with no annotation support.

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 a single, concise sentence that directly states the tool's function. It is front-loaded with the action and resource, and contains no extraneous words. Every word earns its place.

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?

Given the tool has no parameters, no output schema, and no annotations, the description is minimal but adequate. It communicates the core purpose. However, it could be improved by clarifying what 'canonical pricing entry point' means (e.g., URL, object) to fully equip the agent.

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?

There are zero parameters, so the description naturally adds no parameter-level details. The baseline for 0 parameters is 4, and the description correctly communicates the tool's purpose. It adds value by explaining the return value.

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 tool returns the 'canonical pricing entry point' for SeedanceAI. It uses a specific verb ('Return') and resource ('pricing entry point'), and it distinguishes itself from siblings (list_styles, get_official_links) which handle different concerns.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. It does not mention context, prerequisites, or conditions for use, leaving the agent without clarity on when this tool is appropriate.

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

list_stylesA

Return the canonical list of image-generation styles or presets the site exposes. (SeedanceAI)

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A4.2/5.0
Behavior4/5

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

No annotations exist, so the description bears full responsibility. It discloses a read-only operation (return list) with no side effects. While it does not elaborate on potential dynamic behavior or constraints, the simplicity of a parameterless list tool makes this acceptable.

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 a single, front-loaded sentence with no extraneous information. Every word contributes to the purpose.

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 zero parameters, no output schema, and no annotations, the description covers the essential functionality. It could note whether the list is static or dynamic, but the current level is adequate for a simple list retrieval.

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?

There are zero parameters, and the description provides no parameter information, which is appropriate. Baseline for 0 parameters is 4; no additional detail is needed.

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 tool returns the canonical list of image-generation styles, with a specific verb and resource. It distinguishes itself from sibling tools (get_pricing, get_official_links) which serve different purposes.

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 for retrieving available styles, but provides no explicit guidance on when to use this tool versus alternatives or any prerequisites. The purpose is clear, but context for selection is missing.

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. Dates show when Glama detected each change.

  1. 3 tool updatesv0.1.0
    • First observedget_official_links
    • First observedget_pricing
    • First observedlist_styles
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4/5.0
Disambiguation5/5

Each tool retrieves a distinct type of information (styles, pricing, links) with no overlap.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern with lowercase underscores: list_styles, get_pricing, get_official_links.

Tool Count5/5

Three tools is appropriate for an informational server, providing a focused scope without unnecessary complexity.

Completeness4/5

Covers the main information retrieval needs for SeedanceAI, but lacks tools for image generation or style management, which may be expected given the platform.

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/rocnubie/seedanceai-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server