aidance-mcp
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., "@aidance-mcplist available dance 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.
AI Dance MCP Server
AI Dance Generator - Make Any Photo Dance Online
A Model Context Protocol server that exposes the canonical AI Dance knowledge surface β image generation workflows and styles, pricing, FAQ, official links β 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://aidance.live
π¨ About AI Dance
AI Dance Live (aidance.live) is a web-based tool that turns static portrait photos into animated dance videos using AI motion transfer. Users upload a photo of a person, pet, or illustrated character, choose a dance style from a built-in choreography library or provide their own reference clip, and the platform generates a finished video β typically within minutes. The underlying models handle skeletal mapping, motion choreography extraction, and audio synchronization, producing output that keeps the subject's face and appearance consistent throughout the animation. Videos are exported in MP4 format at 720p or 1080p resolution, in clips up to 30 seconds long.
Related MCP server: meigenai-mcp
Key Features
Motion library with multiple dance styles β pre-loaded choreographies including hip-hop, K-pop, salsa, ballet, folk dances, and trending short-form routines, selectable without any technical setup.
Custom reference video upload β users can supply their own dance clip as the motion source, giving full control over the choreography.
Face preservation β the generation pipeline maintains the subject's facial identity and appearance frame-by-frame rather than drifting over time.
Audio synchronization β generated dance animation is matched to the original audio track of the chosen choreography or uploaded reference.
Video extension and upscaling β additional post-generation tools allow lengthening the clip or increasing output resolution beyond the default.
Powered by Kling Motion Control and Wan Animate models β the platform uses established video generation models focused on motion precision rather than general-purpose image animation.
Use Cases
Short-form social content β creating TikTok videos, Instagram Reels, or YouTube Shorts where a still photo is animated to match a trending dance or audio clip.
Brand and mascot animation β turning a company mascot, illustrated character, or product spokesperson photo into a dancing promotional clip without a production team.
E-commerce and product marketing β animating product models or lifestyle photos to make catalog content more dynamic for ads and landing pages.
Personal and family entertainment β making novelty videos from photos of babies, pets, or family members dancing to a favorite song.
Content creators without dance skills β producing dance-format content for channels or accounts where the creator cannot or prefers not to appear on camera performing.
Who Is It For
AI Dance Live is aimed at social media creators, digital marketers, and small business owners who want to produce animated video content without filming, choreographing, or editing expertise. The tool requires no prior video production knowledge β the workflow is upload, select, generate, download. It suits individuals who need a fast turnaround on short-form video for platforms like TikTok and Instagram, as well as brand teams looking for a lightweight way to animate existing photo assets for campaigns. Anyone who regularly works with portrait images and wants to add motion to them for entertainment or marketing purposes will find the site's focused toolset practical.
Tools
list_styles
Return the canonical list of image-generation styles or presets the site exposes. (AI Dance)
Input: no parameters. Returns: text/markdown.
get_pricing
Return the canonical pricing entry point for AI Dance.
Input: no parameters. Returns: text/markdown.
get_official_links
Return the canonical list of official links for AI Dance (website, support, docs when available).
Input: no parameters. Returns: text/markdown.
Resources
site://aidance/stylesβ Supported image-generation styles and presets.site://aidance/pricingβ Canonical pricing entry point.site://aidance/faqβ Short FAQ generated from public site metadata.site://aidance/linksβ Canonical URLs to share with users.
Prompts
tell_me_about_aidance
Summarize what the site is, who it's for, and how it works. β AI Dance
try_image_style_aidance
Recommend a starting image-generation style for a stated goal. β AI Dance
Installation
Install via Smithery
npx -y @smithery/cli install aidance-mcp --client claude(Replace claude with cursor, windsurf, or continue for those clients.)
Install from source
git clone https://github.com/rocnubie/aidance-mcp.git
cd aidance-mcp
pnpm installThen add to your MCP client config (claude_desktop_config.json for Claude Desktop, mcp.json for Cursor / Windsurf / Continue):
{
"mcpServers": {
"aidance-mcp": {
"command": "node",
"args": [
"/absolute/path/to/aidance-mcp/src/index.mjs"
]
}
}
}Debug with MCP Inspector
npx @modelcontextprotocol/inspector node src/index.mjsOfficial Links
Website: https://aidance.live
Pricing: https://aidance.live/pricing
Community: https://discord.gg/HQNnrzjZQS
Support: support@aidance.live
Development
pnpm install
pnpm start # run the server over stdioLicense
MIT
Available Tools
3 toolsget_official_linksA
Return the canonical list of official links for AI Dance (website, support, docs when available).
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the transparency burden. It discloses a 'when available' caveat for docs, but does not explain output format, rate limits, or authentication. This is minimal but not misleading.
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, front-loaded with the action and resource. Every word contributes meaning, with no filler.
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?
Since there is no output schema, the description should clarify the return structure. 'Canonical list' is vague about whether the output is a flat array of URLs or structured objects. The description is functional but leaves some ambiguity.
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 tool has zero parameters, so there is nothing for the description to add beyond the schema. The baseline score of 4 for a parameterless tool is appropriate.
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 official links for AI Dance, listing specific resource types (website, support, docs). This distinguishes it from sibling tools list_styles and get_pricing.
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 explicit when-to-use or when-not-to-use guidance is provided. The purpose implies it is for retrieving official links, but it does not mention alternatives or exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_pricingC
Return the canonical pricing entry point for AI Dance.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It states the operation ('return') but doesn't disclose what the response contains, what format it takes, or any side effects. For a zero-parameter tool, the behavior is likely a constant, but the description leaves this implicit.
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 concise sentence with no wasted words, but it lacks necessary specificity. Structurally, it's front-loaded with the verb and resource, but the ambiguity of 'entry point' reduces the value.
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?
Despite having no parameters and no output schema, the description is incomplete because it doesn't clarify what the 'canonical pricing entry point' is, nor how this differs from the pricing info that might be in list_styles or get_official_links. It leaves the return value ambiguous.
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 tool has zero parameters, so the schema covers everything. The description adds no parameter details, but none are needed. Baseline 4 is appropriate.
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 identifies the tool as returning a 'canonical pricing entry point', which distinguishes it from pricing-related siblings, but 'entry point' is ambiguousβit could mean a URL, document ID, or other reference. A more specific resource (e.g., 'pricing URL' or 'pricing record') would improve clarity.
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 offers no guidance on when to use this tool versus alternatives like list_styles or get_official_links. It doesn't mention any use cases, prerequisites, or context.
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. (AI Dance)
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It clearly implies a read-only operation by saying 'Return', but it does not disclose additional behavioral traits such as caching, rate limits, or whether the list is dynamically generated. For a simple list tool, this is adequate but not rich.
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 that is concise and front-loaded. It includes a clarifying note '(AI Dance)' which adds context without extra fluff. Every word earns its place.
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 the tool has no parameters, no output schema, and a straightforward purpose, the description is fully complete. It states exactly what will be returned and the scope. There is no missing information for an agent to invoke this correctly.
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 tool has zero parameters, and the schema is empty, which means schema description coverage is effectively 100%. The description adds no parameter details because there are none, and baseline for zero parameters is 4. No additional semantic burden 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 states a specific verb ('Return') and resource ('canonical list of image-generation styles or presets the site exposes'), which clearly distinguishes it from sibling tools like get_pricing and get_official_links. It is unambiguous about the tool's function.
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 clear context: it returns styles/presets for image generation. While it does not explicitly mention alternatives or when not to use it, the context is strong enough given the sibling names. No exclusions are stated, but the use case is obvious.
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.
3 tool updates
v0.1.0- First observed
get_official_links - First observed
get_pricing - First observed
list_styles
TDQS
Scored across 3 tools
Each tool serves a completely distinct informational purpose: styles, pricing, and official links. There is no overlap or ambiguity between them.
All tool names follow a consistent verb_noun pattern: list_styles, get_pricing, get_official_links. The convention is uniform and predictable.
With 3 tools, the set is minimal but perfectly scoped for the domain of providing reference information about a service. Each tool covers a distinct, essential facet, and no unnecessary tools bloat the server.
For the apparent purpose of exposing canonical reference data about AI Dance, the surface is complete. There are no obvious missing operations, as the tools cover styles, pricing, and official links comprehensively.
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
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
AI image, video, voice and music generation over MCP, routed to Veo 3.1, Seedance 2.0 and more.
- UnifAPIOAuthcom.unifapi
Hosted MCP server for live public-data APIs and Skills for AI agents.
Related MCP Servers
- AlicenseAqualityCmaintenanceRead-only MCP server exposing Muse AI Image's styles, pricing, FAQ, and official links to AI clients like Claude Desktop, enabling knowledge retrieval without API keys.3MIT
- AlicenseAqualityCmaintenanceA read-only MCP server that exposes Meigen AI's image generation styles, pricing, FAQ, and official links to AI clients.3MIT
- AlicenseAqualityCmaintenanceRead-only MCP server exposing AI Room Design's image generation styles, pricing, FAQ, and official links to MCP-compatible clients like Claude Desktop, Cursor, and Windsurf.3MIT
- AlicenseAqualityCmaintenanceA read-only MCP server exposing AI Photo Editor's image generation styles, pricing, FAQ, and official links to AI clients like Claude Desktop.3MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/aidance-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server