Mcp Happyhorse

io.github.AceDataCloudv2026.10.4.1Updated Oct 4, 2026

Generate and edit Happy Horse AI videos through Ace Data Cloud

VerifiedStreamable HTTPWeb executableAI & MLMedia & Design

Overview

AI-generated overview

Lets an assistant generate and edit Happy Horse AI videos from text, images, or reference images via Ace Data Cloud.

What it does
Wraps the Happy Horse video API with tools for text-to-video, first-frame image animation, reference-to-video from 1-9 images, and video editing with up to 5 reference images. It also exposes task polling tools for single and batch jobs and a model listing tool. Generation runs asynchronously: the assistant keeps the returned task_id and polls until a final video_url or error appears. Outputs are 720P or 1080P, 3-15 seconds long.
When to use it
Use it when an assistant should produce short AI videos or edit existing clips as part of a conversation, for example turning a prompt or a still image into a clip, or restyling a source video. It suits users already on Ace Data Cloud who want video generation without building their own API integration.
Requirements
A remote endpoint at happyhorse.mcp.acedata.cloud or a local process installed from PyPI (mcp-happyhorse, run with uvx or pip). Local stdio mode needs the ACEDATACLOUD_API_TOKEN environment variable; the hosted endpoint accepts a Bearer token header or OAuth. A token comes from the Ace Data Cloud platform. Network access to the Ace Data Cloud API is required.
Before you install
The server requires the ACEDATACLOUD_API_TOKEN secret, which authorizes API calls and may incur charges on the Ace Data Cloud account. Generation and editing submit jobs to a third-party service, so prompts, images, and videos are sent to Ace Data Cloud. Video generation is asynchronous and consumes credits or quota; check pricing before heavy use.

Installation

In SourceWeft

  1. Open Mcp Happyhorse in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "mcp-happyhorse": {
      "type": "http",
      "url": "https://happyhorse.mcp.acedata.cloud/mcp"
    }
  }
}

README

Happy Horse MCP Server

[PyPI] [Python] [License]

Model Context Protocol server for Happy Horse AI video generation and editing through the Ace Data Cloud API.

Capabilities

  • Text-to-video generation
  • First-frame image-to-video animation
  • Reference-to-video generation with 1-9 subject or style images
  • Video editing with up to 5 reference images
  • 720P and 1080P output
  • Single and batch task polling
  • Local stdio and hosted Streamable HTTP/SSE transports
  • Direct Bearer token and AceDataCloud OAuth authentication

Install

bash
pip install mcp-happyhorseexport ACEDATACLOUD_API_TOKEN="your-token"mcp-happyhorse

Get a token from platform.acedata.cloud.

Configure

Claude Desktop

json
{  "mcpServers": {    "happyhorse": {      "command": "uvx",      "args": ["mcp-happyhorse"],      "env": {        "ACEDATACLOUD_API_TOKEN": "your-token"      }    }  }}

Hosted MCP

json
{  "mcpServers": {    "happyhorse": {      "url": "https://happyhorse.mcp.acedata.cloud/mcp",      "headers": {        "Authorization": "Bearer your-token"      }    }  }}

The hosted endpoint also supports OAuth-capable MCP clients.

Tools

ToolPurpose
happyhorse_generate_videoGenerate a video from text
happyhorse_generate_video_from_imageAnimate one first-frame image
happyhorse_generate_video_from_referencesGenerate from 1-9 reference images
happyhorse_edit_videoEdit a source video with up to 5 references
happyhorse_get_taskQuery one task
happyhorse_get_tasks_batchQuery multiple tasks
happyhorse_list_modelsList valid models for each action

Generation tools submit asynchronously when no callback_url is supplied. Keep the returned task_id, wait about 15 seconds, then call happyhorse_get_task until the response contains a final video_url or terminal error.

Models

ActionModelsDefault
Text-to-videohappyhorse-1.0-t2v, happyhorse-1.1-t2vhappyhorse-1.1-t2v
Image-to-videohappyhorse-1.0-i2v, happyhorse-1.1-i2vhappyhorse-1.1-i2v
Reference-to-videohappyhorse-1.0-r2v, happyhorse-1.1-r2vhappyhorse-1.1-r2v
Video edithappyhorse-1.0-video-edithappyhorse-1.0-video-edit

Generation duration is 3-15 seconds. Supported resolutions are 720P and 1080P. Text and reference generation support 16:9, 9:16, 1:1, 4:3, and 3:4. Image-to-video follows the input image ratio. Video-edit duration follows the source video.

Example Requests

Ask your MCP client:

Generate a 720P, 9:16 video of a white horse crossing a snowy ridge at sunrise.

Animate https://example.com/horse.jpg with a slow camera push and wind moving the mane.

Edit https://example.com/source.mp4 to preserve the camera motion but apply the costume style from https://example.com/reference.jpg. Keep the original audio.

Environment

VariableDefaultPurpose
ACEDATACLOUD_API_TOKENnoneAPI token for local stdio mode
ACEDATACLOUD_API_BASE_URLhttps://api.acedata.cloudAPI origin
HAPPYHORSE_REQUEST_TIMEOUT60HTTP request timeout in seconds
MCP_TRANSPORTstdiostdio or http
MCP_SERVER_URLnonePublic URL that enables hosted OAuth
LOG_LEVELINFOLogging level

Development

bash
pip install -e ".[all]"pytest --cov=core --cov=toolsruff check .mypy core tools main.py

Documentation

Documentation

License

MIT

Source: README.md at commit 2be1ac9

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v2026.10.4.1LatestOct 4, 2026