What is Mcp Video Recognition

MCP Video Recognition is a server that utilizes Google’s Gemini AI to provide tools for recognizing and analyzing images, audio, and videos.

Use cases

Use cases include analyzing video content for specific objects or actions, transcribing audio for accessibility, and generating descriptions for images.

How to use

To use MCP Video Recognition, clone the repository from GitHub, install the necessary dependencies, and build the project. You can also integrate it with clients like Cline using configuration files.

Key features

Key features include image recognition, audio recognition, and video recognition, all powered by Google Gemini AI.

Where to use

MCP Video Recognition can be used in various fields such as media analysis, content moderation, security surveillance, and accessibility services.

MCP Video Recognition Server

An MCP (Model Context Protocol) server that provides tools for image, audio, and video recognition using Google’s Gemini AI.

Features

• Image Recognition: Analyze and describe images using Google Gemini AI
• Audio Recognition: Analyze and transcribe audio using Google Gemini AI
• Video Recognition: Analyze and describe videos using Google Gemini AI

Prerequisites

• Node.js 18 or higher
• Google Gemini API key

Installation

Manual Installation

1. Clone the repository:

   git clone https://github.com/yourusername/mcp-video-recognition.git
   cd mcp-video-recognition
   

2. Install dependencies:

   npm install
   

3. Build the project:

   npm run build
   

Installing in FLUJO

1. Click Add Server
2. Copy & Paste Github URL into FLUJO
3. Click Parse, Clone, Install, Build and Save.

Installing via Configuration Files

To integrate this MCP server with Cline or other MCP clients via configuration files:

1. Open your Cline settings:

   • In VS Code, go to File -> Preferences -> Settings
   • Search for “Cline MCP Settings”
   • Click “Edit in settings.json”

2. Add the server configuration to the mcpServers object:

   {
     "mcpServers": {
       "video-recognition": {
         "command": "node",
         "args": [
           "/path/to/mcp-video-recognition/dist/index.js"
         ],
         "disabled": false,
         "autoApprove": []
       }
     }
   }
   

3. Replace /path/to/mcp-video-recognition/dist/index.js with the actual path to the index.js file in your project directory. Use forward slashes (/) or double backslashes (\\) for the path on Windows.

4. Save the settings file. Cline should automatically connect to the server.

Configuration

The server is configured using environment variables:

• GOOGLE_API_KEY (required): Your Google Gemini API key
• TRANSPORT_TYPE: Transport type to use (stdio or sse, defaults to stdio)
• PORT: Port number for SSE transport (defaults to 3000)
• LOG_LEVEL: Logging level (verbose, debug, info, warn, error, defaults to info)

Usage

Starting the Server

With stdio Transport (Default)

GOOGLE_API_KEY=your_api_key npm start

With SSE Transport

GOOGLE_API_KEY=your_api_key TRANSPORT_TYPE=sse PORT=3000 npm start

Using the Tools

The server provides three tools that can be called by MCP clients:

Image Recognition

{
  "name": "image_recognition",
  "arguments": {
    "filepath": "/path/to/image.jpg",
    "prompt": "Describe this image in detail",
    "modelname": "gemini-2.0-flash"
  }
}

Audio Recognition

{
  "name": "audio_recognition",
  "arguments": {
    "filepath": "/path/to/audio.mp3",
    "prompt": "Transcribe this audio",
    "modelname": "gemini-2.0-flash"
  }
}

Video Recognition

{
  "name": "video_recognition",
  "arguments": {
    "filepath": "/path/to/video.mp4",
    "prompt": "Describe what happens in this video",
    "modelname": "gemini-2.0-flash"
  }
}

Tool Parameters

All tools accept the following parameters:

• filepath (required): Path to the media file to analyze
• prompt (optional): Custom prompt for the recognition (defaults to “Describe this content”)
• modelname (optional): Gemini model to use for recognition (defaults to “gemini-2.0-flash”)

Development

Running in Development Mode

GOOGLE_API_KEY=your_api_key npm run dev

Project Structure

• src/index.ts: Entry point
• src/server.ts: MCP server implementation
• src/tools/: Tool implementations
• src/services/: Service implementations (Gemini API)
• src/types/: Type definitions
• src/utils/: Utility functions

License

MIT