Kaltura MCP

🚀 Kaltura Model Context Protocol (MCP) Server

The Kaltura MCP Server implements the Model Context Protocol (MCP), enabling AI models to interact with Kaltura's media management capabilities.

🚀 Quick Start

Run the following command to quickly start the server:

docker run -p 8000:8000 ghcr.io/zoharbabin/kaltura-mcp:latest

Visit http://localhost:8000 to view the documentation.

✨ Features

This server empowers AI models with the following capabilities:

• Upload media to Kaltura
• Retrieve media metadata
• Search for media
• Manage categories
• Manage users and permissions

By implementing the Model Context Protocol, this server allows AI models to interact with Kaltura's API in a standard way, simplifying the integration of Kaltura's features into AI workflows.

📦 Installation

Using Docker

Method 1: Use the pre-built Docker image

The simplest way is to use our pre-built multi-architecture Docker image (supporting x86_64/amd64 and ARM64/Apple Silicon):

# Pull the latest image
docker pull ghcr.io/zoharbabin/kaltura-mcp:latest

# Create a configuration file
cp config.yaml.example config.yaml
# Edit config.yaml with your Kaltura API credentials

# Run the container
docker run -p 8000:8000 -v $(pwd)/config.yaml:/app/config.yaml ghcr.io/zoharbabin/kaltura-mcp:latest

Method 2: Build locally using Docker Compose

Alternatively, you can build the image locally:

# Clone the repository
git clone https://github.com/zoharbabin/kaltura-mcp.git
cd kaltura-mcp

# Build and run using Docker Compose
docker-compose up

Manual Installation

# Clone the repository
git clone https://github.com/zoharbabin/kaltura-mcp.git
cd kaltura-mcp

# Create a virtual environment (requires Python 3.10 or higher)
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install dependencies
pip install -e .

# Configure the server
cp config.yaml.example config.yaml
# Edit config.yaml with your Kaltura API credentials

# Start the server
python -m kaltura_mcp_server

📚 Documentation

Requirements

• Python: Version 3.10 or higher (officially supported: 3.10, 3.11, 3.12)
• Operating System: Linux, macOS, Windows
• Dependencies: See pyproject.toml for the full list

Repository Structure

The kaltura-mcp-public repository contains a complete, self-contained implementation of the Kaltura MCP Server, including:

• All necessary code
• Comprehensive documentation
• Docker support
• Installation scripts
• Example clients
• Test scripts

Configuration

The default configuration file is config.yaml, located at the root of the repository. You can specify the following settings:

bind:
  port: 8000  # The port to bind to, default is 8000
log_level: INFO  # Log level (DEBUG, INFO, WARNING, ERROR, CRITICAL)

💻 Usage Examples

Command Line Interface (CLI)

kaltura-mcp-cli is a command-line tool for interacting with the Kaltura MCP Server. You can install it as follows:

pip install kaltura-mcp-cli

Usage examples:

# Get media metadata
kaltura-mcp-cli get-media-metadata --id=1234

# Search for media
kaltura-mcp-cli search-media --query="猫"

# Manage users
kaltura-mcp-cli create-user --name="新用户" --email="new@example.com"

Python Client Library

kaltura-mcp-client is a Python library for interacting with the Kaltura MCP Server. You can install it as follows:

pip install kaltura-mcp-client

Usage examples:

from kaltura_mcp_client import KalturaMCPClient

# Initialize the client
client = KalturaMCPClient(
    host="localhost",
    port=8000,
    insecure=True  # Disable SSL verification (for testing environments)
)

# Get media metadata
metadata = client.get_media_metadata(id=1234)
print(metadata)

# Search for media
results = client.search_media(query="猫")
print(results)

🤝 Contributing

For detailed information on how to contribute to this project, please refer to CONTRIBUTING.md.

📄 License

This project is released under the AGPLv3 license. Please see the LICENSE file for the full license text.