Ghibli

Provides image-to-video conversion, credits checks, and task status for AI-generated videos.

typescript

4

GitHub Stars

typescript

Language

4 months ago

First Indexed

3 weeks ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "michaelyangjson-mcp-ghibli-video": {
      "command": "npx",
      "args": [
        "-y",
        "@openmcprouter/mcp-server-ghibli-video"
      ],
      "env": {
        "Ghibli_API_URL": "https://www.gpt4oimg.com"
      }
    }
  }
}

You can run an MCP server that exposes AI image and video generation capabilities through a simple, programmable interface. This server focuses on converting images to videos and managing tasks or credits, giving you a compact, extensible workflow you can integrate into your own tools or Claude Desktop workflows.

How to use

You interact with the MCP server through an MCP client or integration that can call the supported endpoints. The key capabilities let you convert an image into a video, check your remaining credits, and poll the status of a video generation task.

Image to Video conversion lets you send a base64-encoded image or an image URL along with your API key to produce an animated video. You can optionally guide the generation with a prompt (default: "in the style of ghibli"), set the aspect ratio (default: "9:16"), and provide a negative prompt to steer results (default: "bad prompt").

Check your available credits using get_points by providing your API key. This helps you manage usage against your plan.

After you start a video generation with image_to_video, you receive a taskId. Use get_task_result with that taskId and your API key to monitor progress and retrieve the final video when it completes.

Available tools

image_to_video

Converts a static image (base64 or URL) into an animated video. Requires an API key and optionally accepts a prompt, aspect ratio, and negative prompt.

get_points

Checks remaining API credits for the provided API key.

get_task_result

Checks the status of an ongoing or completed image_to_video task using the taskId.