Happy Horse MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | Logging level | INFO |
| MCP_TRANSPORT | No | Transport type: stdio or http | stdio |
| MCP_SERVER_URL | No | Public URL that enables hosted OAuth | |
| ACEDATACLOUD_API_TOKEN | Yes | API token for Ace Data Cloud (required for local stdio mode) | |
| ACEDATACLOUD_API_BASE_URL | No | API origin | https://api.acedata.cloud |
| HAPPYHORSE_REQUEST_TIMEOUT | No | HTTP request timeout in seconds | 60 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| happyhorse_list_modelsB | List Happy Horse actions, compatible models, and defaults. |
| happyhorse_get_taskB | Get the status and final video URL for one Happy Horse task. |
| happyhorse_get_tasks_batchB | Get multiple Happy Horse tasks in one request. |
| happyhorse_generate_videoB | Generate a video from a text prompt with Happy Horse. |
| happyhorse_generate_video_from_imageA | Animate a first-frame image with Happy Horse. |
| happyhorse_generate_video_from_referencesB | Generate a video guided by one or more reference images. |
| happyhorse_edit_videoB | Edit a source video using text and optional reference images. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| happyhorse_video_workflow | Explain the recommended Happy Horse workflow. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Each tool targets a distinct action: listing models, retrieving single or batch tasks, generating from text/image/references, and editing video. The generation variants are clearly separated by source type and input description.
All tools follow the same happyhorse_verb_noun naming pattern with snake_case throughout. Variations like generate_video_from_image and generate_video_from_references are logical extensions of the root verb.
Seven tools cover a focused video generation and editing domain without unnecessary extras. This is a well-scoped size that gives agents a clear, manageable set of operations.
The main task lifecycle is covered: model discovery, generation with multiple input modes, editing, and status retrieval including batch. Minor gaps include no list-all-tasks or cancel/delete operations, but these are not essential to the core workflow.