Amazon Nova Reel

This MCP server provides asynchronous video generation capabilities using Amazon Nova Reel 1.1 through AWS Bedrock, enabling AI agents to create videos from text prompts with comprehensive parameter control including duration, frame rate, and dimensions. Built using Python with FastMCP and boto3, it offers four core tools: start_async_invoke for initiating video generation jobs with validation and S3 storage, list_async_invokes and get_async_invoke for monitoring job status and retrieving completed videos, and get_prompting_guide providing detailed best practices based on AWS documentation for effective video prompts including camera control, lighting, and narrative structure. The implementation supports three transport methods (stdio, SSE, HTTP streaming), features persistent job tracking with JSON storage, Docker containerization with multi-architecture support, and includes detailed prompting guidelines covering shot types, camera movements, lighting conditions, and example prompts for different video categories, making it valuable for automated video content creation, marketing material generation, and building AI assistants that need video production capabilities without manual AWS console access.