Skip to main content
Glama

Why This Package?

@runapi.ai/happyhorse-mcp is a focused Model Context Protocol server for the HappyHorse model line on RunAPI. It gives MCP-compatible assistants direct access to 3 endpoints and 7 model variants without loading the full RunAPI catalog.

Use this per-model server when an agent should stay scoped to HappyHorse. Use @runapi.ai/mcp when one assistant should discover every RunAPI model line.


Related MCP server: GPT Image MCP Server

Install

Add it to Claude Code:

claude mcp add happyhorse -s user -- npx -y @runapi.ai/happyhorse-mcp

Use project scope when the server should be shared with a repository:

claude mcp add happyhorse -s project -- npx -y @runapi.ai/happyhorse-mcp

Codex, Cursor, Windsurf, VS Code, Roo Code, and other MCP hosts can use the same stdio command:

{
  "mcpServers": {
    "happyhorse": {
      "command": "npx",
      "args": ["-y", "@runapi.ai/happyhorse-mcp"]
    }
  }
}

check_pricing works before sign-in. For task creation and status polling, ask your assistant to call the login tool. It opens a browser login and saves credentials to ~/.config/runapi/config.json, the same file used by runapi login. Headless and CI hosts can still set RUNAPI_API_KEY before starting the MCP host.

Ready-made examples are in examples/ for Claude, Cursor, Windsurf, VS Code, and Roo Code.


Tools

Tool

Auth

Purpose

edit_video

Yes

Create a HappyHorse edit video task and optionally wait for a terminal status. Returns the task id, status, and output URLs.

image_to_video

Yes

Create a HappyHorse image to video task and optionally wait for a terminal status. Returns the task id, status, and output URLs.

text_to_video

Yes

Create a HappyHorse text to video task and optionally wait for a terminal status. Returns the task id, status, and output URLs.

get_task

Yes

Fetch the current status and latest payload for an existing task.

check_pricing

No

Look up current pricing for a HappyHorse model and endpoint.


Models

HappyHorse covers 7 model variants across 3 endpoints. Each tool accepts the models listed for it:

Tool

Models

edit_video

happyhorse-edit-video

image_to_video

happyhorse-1.0-i2v, happyhorse-image-to-video

text_to_video

happyhorse-1.0-r2v, happyhorse-1.0-t2v, happyhorse-character, happyhorse-text-to-video

Model availability can change between releases. Use check_pricing or the HappyHorse model page for the current catalog view.


Agent Prompts

Ask your assistant in natural language; it can inspect pricing, create the task, and return the task id plus output URLs.

Create a task

Run a HappyHorse edit video task with RunAPI.

The assistant can call check_pricing, then edit_video, and return the task id, status, and output URLs.

Submit without waiting

Create the task but don't wait for it to finish.

The assistant calls the create tool with wait: false and returns the task id. Check on it later with get_task.

Check pricing before creating

Check current HappyHorse pricing, then create the task if it matches my request.

The assistant calls check_pricing and can link to the HappyHorse model page for the canonical catalog entry.


Configuration

The server resolves auth in this order:

  1. RUNAPI_API_KEY environment variable, useful for headless and CI hosts

  2. ~/.config/runapi/config.json, created by the MCP login tool or runapi login

  3. No key, which still allows check_pricing

The config file is normally managed by login. A pre-provisioned headless config can use:

{
  "apiKey": "your_runapi_key"
}

Do not commit real API keys.


Resource

URL

HappyHorse model page

https://runapi.ai/models/happyhorse

npm package

@runapi.ai/happyhorse-mcp

GitHub repository

runapi-ai/happyhorse-mcp

RunAPI MCP overview

runapi.ai/mcp

RunAPI docs

runapi.ai/docs


License

Licensed under the Apache License, Version 2.0.

Available Tools

6 tools
check_pricingB

Look up RunAPI pricing for the happyhorse model line.

Inputs: model, action.

edit_videoB

Create a HappyHorse task on RunAPI (edit video). Returns a task id, status, and output URLs.

Inputs: source_video_url (required), seed, wait, model, +7 more.

get_taskB

Fetch the current status and latest result payload for a happyhorse task.

Inputs: action (required), task_id (required).

image_to_videoC

Create a HappyHorse task on RunAPI (image to video). Returns a task id, status, and output URLs.

Inputs: first_frame_image_url (required), seed, wait, model, +6 more.

loginA

Authenticate RunAPI by opening a browser PKCE login flow and saving the API key to ~/.config/runapi/config.json.

Inputs: force.

text_to_videoC

Create a HappyHorse task on RunAPI (text to video). Returns a task id, status, and output URLs.

Inputs: seed, wait, model, prompt, +7 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.5/5.0

    Scored across 6 tools

    Disambiguation5/5

    Each tool targets a clearly distinct operation: three video creation modes based on input type (edit, image-to-video, text-to-video), task status retrieval, pricing lookup, and authentication. There is no overlap or ambiguity between tools.

    Naming Consistency4/5

    All names use consistent snake_case with verb-based naming. 'login' is the only tool that does not follow a verb_noun pattern, which is a minor deviation but still clear.

    Tool Count5/5

    Six tools cleanly cover the essential workflow: three generation modes, status checking, pricing, and authentication. The count is well-scoped with no redundant or unnecessary tools.

    Completeness4/5

    The core create-and-poll workflow is fully supported. However, task lifecycle operations like listing, cancelling, or deleting tasks are missing, and pricing is only available for the model line, leaving minor gaps.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers