This hands-on project demonstrates how to develop a flexible media workflow creation tool using the Strands SDK and AWS Elemental Media Services. Learn to streamline the creation, management, and troubleshooting of complex media workflows by leveraging Strands Agents and Model Context Protocol (MCP) servers for natural language interactions.
Transform complex AWS Media Services operations into simple natural language commands. This project shows you how to build intelligent agents that can create, modify, and troubleshoot live streaming workflows through conversational interfaces.
Architecture diagram showing the complete media workflow orchestration using Agentic AI, MCP servers, and AWS Media Services
- Agentic AI Integration: Build intelligent agents using the Strands SDK
- Media Workflow Automation: Orchestrate AWS Elemental MediaLive, MediaPackage, and CloudFront
- Natural Language Processing: Convert plain English into complex media service configurations
- MCP Server Development: Create custom Model Context Protocol servers for AWS services
- Workflow Management: Handle end-to-end live streaming pipelines programmatically
- AWS Account with appropriate permissions
- IAM Access to the following services:
- AWS Elemental MediaLive
- AWS Elemental MediaPackage
- AWS Elemental MediaConnect
- Amazon S3
- Amazon CloudFront
- Amazon Bedrock (for AI capabilities)
- AWS CLI configured with your credentials
- Python 3.11+
- Jupyter Notebook or JupyterLab
- uv package manager (recommended for dependency management)
# Clone the repository
git clone <repository-url>
cd sample-aws-mediaops-agentic-ai# Configure AWS CLI (if not already done)
aws configure
# Verify access to required services
aws sts get-caller-identity
aws bedrock list-foundation-models --region us-east-1# Start Jupyter using uv
uv run jupyter lab
# Or use Jupyter Notebook
uv run jupyter notebookNavigate through the numbered directories in order:
- 10 Prerequisite - Environment setup and validation
- 20 MCP Servers for Media Workflow - Build custom MCP servers
- 30 Create Live Stream Using Kiro CLI - Agent configuration and deployment
- 40 Modify Live Stream Using AWS Strands Agents - Advanced workflow management
- 60 Agent Prompt Management - Customize agent behavior
sample-aws-mediaops-agentic-ai/
├── 10 Prerequisite/ # Setup and requirements
├── 20. MCP Servers for Media Workflow/ # Custom MCP server implementations
├── 30 Create Live Stream Using Kiro CLI/
│ ├── 31 Build and Configure Media Workflow Agent/
│ ├── 32 Build and Configure Media Workflow Prompts/
│ └── 34 Create a Live Streaming Media Workflow/
├── 40 Modify Live stream Using AWS Strands Agents/
│ ├── 41 Build Media Workflow Agent Using Strands/
│ ├── 42 Modify a Live Streaming Media Workflow/
│ └── 43 Troubleshoot Media Workflow Using Agent/
├── 60 Agent Prompt Management/ # Agent customization tools
└── requirements.txt # Python dependencies
The sample code; software libraries; command line tools; proofs of concept; templates; or other related technology (including any of the foregoing that are provided by our personnel) is provided to you as AWS Content under the AWS Customer Agreement, or the relevant written agreement between you and AWS (whichever applies). You should not use this AWS Content in your production accounts, or on production or other critical data. You are responsible for testing, securing, and optimizing the AWS Content, such as sample code, as appropriate for production grade use based on your specific quality control practices and standards. Deploying AWS Content may incur AWS charges for creating or using AWS chargeable resources, such as running Amazon EC2 instances or using Amazon S3 storage.
See LICENSE.
See CONTRIBUTING
See NOTICES.