
zoharbabin/kaltura-mcp
Developer toolsこのページは AI により自動翻訳されています。技術的な詳細は原文をご確認ください。 原文を見る
Kaltura-MCP server powering agentic AI workflows with Kaltura's API
概要
A Model Context Protocol (MCP) server that provides secure, read-only tools for managing Kaltura API operations. This server enables AI assistants to search, discover, and analyze Kaltura media content safely. - : Search and browse media entries with advanced filtering - : Access captions, transcripts, and attachment content - : Browse and explore content categories - : Retrieve viewing analytics and performance metrics - : Read-only operations with comprehensive input validation - : Automatic session handling with configurable expiry This server supports two deployment modes: Personal use, direct Claude Desktop integration, development Hosted services, multiple users, production deployments The script will guide you through: 1. Choosing between stdio (local) or remote mode 2. Securely entering your Kaltura credentials 3. Generating a .env file with proper permissions (600) 4.
README
以下は原文 README の抜粋です。原文を見る。
Kaltura MCP Server
A Model Context Protocol (MCP) server that provides secure, read-only tools for managing Kaltura API operations. This server enables AI assistants to search, discover, and analyze Kaltura media content safely.
Features
- Media Discovery: Search and browse media entries with advanced filtering
- Content Analysis: Access captions, transcripts, and attachment content
- Category Management: Browse and explore content categories
- Analytics: Retrieve viewing analytics and performance metrics
- Secure Access: Read-only operations with comprehensive input validation
- Session Management: Automatic session handling with configurable expiry
Installation
- Clone this repository:
git clone https://github.com/zoharbabin/kaltura-mcp.git
cd kaltura-mcp
- Install dependencies:
pip install -e .
Usage Modes
This server supports two deployment modes:
🔧 Local MCP Server (Stdio Mode)
Best for: Personal use, direct Claude Desktop integration, development
🌐 Remote MCP Server (HTTP/SSE Mode)
Best for: Hosted services, multiple users, production deployments
Local MCP Server Setup (Claude Desktop)
Step 1: Install Package
pip install kaltura-mcp
Step 2: Setup Environment Configuration
🔒 Secure Method (Recommended): Use the interactive setup script:
# Navigate to your project directory
cd /path/to/kaltura-mcp
# Run the interactive setup
python setup_env.py
The script will guide you through:
- Choosing between stdio (local) or remote mode
- Securely entering your Kaltura credentials
- Generating a
.envfile with proper permissions (600) - Providing the exact Claude Desktop configuration
📋 Manual Method: Copy and edit the example file:
# Copy the example file
cp .env.example .env
# Edit with your credentials
# - For stdio mode: Only fill in KALTURA_* variables
# - For remote mode: Fill in JWT_SECRET_KEY, OAUTH_*, and SERVER_* variables
nano .env
# Set secure permissions
chmod 600 .env
Step 3: Get Your Kaltura Credentials
You’ll need these credentials from your Kaltura account:
- Service URL: Your Kaltura server URL (usually
https://cdnapisec.kaltura.com) - Partner ID: Your numeric partner ID (found in KMC → Settings → Integration Settings)
- Admin Secret: Your API admin secret key (found in KMC → Settings → Integration Settings)
- User ID: Your Kaltura user ID (usually your email or
admin)
Step 4: Configure Claude Desktop
Open your Claude Desktop configuration file:
macOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
🔒 Secure Configuration (credentials in .env file):
{
"mcpServers": {
"kaltura": {
"command": "/full/path/to/kaltura-mcp"
}
}
}
Important Notes:
インストール
This server does not publish a one-line install command.
Open the repository installation guide MCP 初心者?mcpskill.org のガイドから始めましょう →設定
{
"mcpServers": {
"kaltura": {
"command": "/full/path/to/kaltura-mcp"
}
}
}