Skip to main content
Glama

mcp-server-ghibli MCP Server

A TypeScript-based MCP server that provides AI image and video generation capabilities through a simple interface.

Note: This server requires an API key from GPT4O Image Generator. Please visit the website to obtain your API key before using this service.

Features

Tools

1. Image to Video Conversion

  • image_to_video - Convert static images into animated videos

    • Required parameters:

      • image: Base64 encoded image or image URL

      • api_key: Authentication key

    • Optional parameters:

      • prompt: Text prompt to guide video generation (default: "in the style of ghibli")

      • aspect_ratio: Output video aspect ratio (default: "9:16")

      • negative_prompt: Negative prompt to guide generation (default: "bad prompt")

2. Points Management

  • get_points - Check remaining API credits

    • Required parameters:

      • api_key: Authentication key

3. Task Management

  • get_task_result - Check the status of a video generation task

    • Required parameters:

      • taskId: Task ID returned from image_to_video

      • api_key: Authentication key

Related MCP server: HeyBeauty MCP Server

Development

Install dependencies:

npm install

Build the server:

npm run build

For development with auto-rebuild:

npm run watch

Installation

To use with Claude Desktop, add the server config:

On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json

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

Installing via Smithery

To install mcp-server-ghibli MCP Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @MichaelYangjson/mcp-ghibli-video --client claude

Debugging

Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:

npm run inspector

The Inspector will provide a URL to access debugging tools in your browser.

Available Tools

3 tools
get_pointsC

Get remaining points

Inputs: api_key (required).

get_task_resultC

Get task result

Inputs: taskId (required), api_key (required).

image_to_videoC

Convert image to animated video

Inputs: image (required), api_key (required), prompt, aspect_ratio, +1 more.

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    C2.6/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose with no overlap: get_points retrieves points, get_task_result fetches task results, and image_to_video handles video conversion. An agent can easily differentiate them based on their specific functions.

    Naming Consistency4/5

    The tools follow a consistent verb_noun pattern (get_points, get_task_result, image_to_video), with minor deviations in verb usage (get vs. image_to). The naming is readable and mostly predictable, though not perfectly uniform.

    Tool Count2/5

    With only 3 tools, the set feels thin for a video server's apparent scope, lacking operations like video management, task creation, or point usage. This minimal count may limit agent workflows and indicate incomplete coverage.

    Completeness2/5

    There are significant gaps in the tool surface for a video server domain: no tools for creating tasks, managing videos, or using points, and core operations like video playback or editing are missing. This will likely cause agent failures in handling typical video-related workflows.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      A TypeScript server that integrates Google's Gemini Pro model with Claude Desktop through the Model Context Protocol, allowing Claude users to access Gemini's text generation capabilities.
      7
      218 npm
      12
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      A TypeScript-based MCP server that implements virtual try-on capabilities using the HeyBeauty API, allowing users to visualize how clothes would look on them through Claude.
      45 npm
      19
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      A TypeScript-based Model Context Protocol server that enables Claude Desktop to fetch real-time weather data via external weather APIs. It provides a simple integration for users to query current weather information through natural language interactions.
      9 npm
      ISC