kaltura-mcp-legacy
If you are the rightful owner of kaltura-mcp-legacy and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
The Kaltura Model Context Protocol (MCP) Server is an implementation of the Model Context Protocol that integrates AI models with Kaltura's media management capabilities.
Kaltura Model Context Protocol (MCP) Server
The Kaltura MCP Server is an implementation of the Model Context Protocol (MCP) that provides AI models with access to Kaltura's media management capabilities.
Overview
This server enables AI models to:
- 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 standardized way, making it easier to integrate Kaltura's capabilities into AI workflows.
Requirements
- Python: 3.10 or higher (3.10, 3.11, 3.12 are officially supported)
- Operating Systems: Linux, macOS, Windows
- Dependencies: See
pyproject.toml
for a complete list
Repository Structure
The kaltura-mcp-public
repository contains the complete, self-contained Kaltura MCP server implementation, including:
- All necessary code
- Comprehensive documentation
- Docker support
- Setup script
- Example clients
- Test scripts
Installation
Using Docker
Option 1: Using Pre-built Docker Image
The easiest way to get started is with our pre-built multi-architecture Docker image (supports both x86_64/amd64 and ARM64/Apple Silicon):
# Pull the latest image
docker pull ghcr.io/zoharbabin/kaltura-mcp:latest
# Create a config 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
Option 2: Building Locally with 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 with 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 (Python 3.10 or higher required)
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
# Run the server
python -m kaltura_mcp.server
Configuration
The Kaltura MCP Server supports a unified configuration system that works with both YAML and JSON formats. To get started:
- Copy
config.yaml.example
toconfig.yaml
and edit it with your Kaltura API credentials:
kaltura:
partner_id: YOUR_PARTNER_ID
admin_secret: YOUR_ADMIN_SECRET
user_id: YOUR_USER_ID
service_url: https://www.kaltura.com/api_v3
- You can also use environment variables for configuration:
export KALTURA_PARTNER_ID=YOUR_PARTNER_ID
export KALTURA_ADMIN_SECRET=YOUR_ADMIN_SECRET
export KALTURA_USER_ID=YOUR_USER_ID
For more detailed configuration options, see the .
Usage
With Claude
To use the Kaltura MCP Server with Claude, see the guide.
With the MCP CLI
To use the Kaltura MCP Server with the MCP CLI, see the guide.
Programmatically
To use the Kaltura MCP Server programmatically, see the directory.
Available Tools
The Kaltura MCP Server provides the following tools:
media_upload
: Upload media files to Kalturamedia_get
: Retrieve media metadatamedia_update
: Update media metadatamedia_delete
: Delete mediacategory_list
: List categoriescategory_get
: Retrieve category metadatacategory_add
: Add a new categorycategory_update
: Update category metadatacategory_delete
: Delete a categoryuser_list
: List usersuser_get
: Retrieve user metadatauser_add
: Add a new useruser_update
: Update user metadatauser_delete
: Delete a user
Available Resources
The Kaltura MCP Server provides the following resources:
media://{entry_id}
: Media entry metadatacategory://{category_id}
: Category metadatauser://{user_id}
: User metadata
Contributing
See for details on how to contribute to this project.
License
This project is licensed under the AGPLv3 License - see the file for details.