Nova Reel Video Mcp
@mirecekd
A Model Context Protocol (MCP) server for Amazon Nova Reel 1.1 video generation using AWS Bedrock. This server provides tools for asynchronous video generation with comprehensive prompting guidelines and both stdio and SSE transport support.
Overview
What is Nova Reel Video MCP?
Nova Reel Video MCP is a Model Context Protocol (MCP) server for Amazon Nova Reel 1.1 video generation using AWS Bedrock. It provides tools for asynchronous video generation with comprehensive prompting guidelines and supports stdio, SSE, and HTTP Streaming transports. It is intended for developers who want to integrate AI-powered video generation into their applications or AI assistants.
How to use Nova Reel Video MCP?
Install via Docker (pre‑built images) or locally with pip install -e . or uvx. Configure AWS credentials and an S3 bucket as environment variables or CLI arguments. Add the server to your MCP client configuration (e.g., Cline or Claude Desktop) or run the SSE/HTTP Streaming version as a standalone web server. Use the four tools: start_async_invoke, list_async_invokes, get_async_invoke, and get_prompting_guide.
Key features of Nova Reel Video MCP
- Asynchronous video generation with job monitoring
- Multiple transport methods: stdio, SSE, and HTTP Streaming
- Built‑in prompting guide based on AWS documentation
- Docker support for all transport variants
- Full integration with AWS Bedrock and S3
Use cases of Nova Reel Video MCP
- Generate short video clips from text prompts for content creation
- Automate video production by chaining generation and retrieval
- Incorporate video generation into AI assistants like Claude Desktop
- Test and prototype video prompts before production use
FAQ from Nova Reel Video MCP
What are the prerequisites for using the server?
Python 3.8+, an AWS account with Bedrock access, an S3 bucket for output, and AWS credentials with the required permissions (bedrock:InvokeModel, bedrock:StartAsyncInvoke, bedrock:GetAsyncInvoke, bedrock:ListFoundationModels, and S3 operations).
How are generated videos stored and accessed?
Videos are stored in your S3 bucket under a folder named by the job ID (s3://your-bucket/job-id/output.mp4). Each completed job returns an HTTPS URL to the video.
What are the supported video specifications?
Duration: 12–120 seconds (must be multiples of 6). Frame rate: 24 fps (recommended). Dimensions: 1280x720 (HD). Format: MP4. Model: amazon.nova-reel-v1:1.
Are there any known limitations or caveats?
Jobs are tracked in memory and are lost if the server restarts; for production use, implement persistent storage. Duration must be a multiple of 6 seconds. The only supported dimension is 1280x720.
What transport and authentication options are available?
The server supports stdio (direct MCP client integration), SSE (web interface on port 8000), and HTTP Streaming (bidirectional transport on port 8001). Authentication uses AWS credentials passed via CLI arguments or environment variables (AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_REGION, S3_BUCKET).