Media Gen

关于

Media Gen is a production-focused, strict TypeScript Model Context Protocol (MCP) server designed to interact with OpenAI Images (gpt-image-1.5, gpt-image-1), OpenAI Videos (Sora), and Google GenAI Videos (Veo). It enables generating and editing images, creating and managing video jobs, and fetching media from URLs or local disk. The tool prioritizes spec-first, type-safe image and video tooling, offering flexible result placements like `resource_link` and inline `image` outputs, optional `sharp` processing, and robust error handling for various MCP-compatible clients.

主要功能

• Strict MCP spec support with first-class CallToolResult objects.
• Full parameter coverage for OpenAI Images (gpt-image-1.5, gpt-image-1) for generation and editing.
• Comprehensive job tooling for OpenAI Videos (Sora) including create, remix, list, retrieve, and delete.
• Google GenAI (Veo) operations for video generation, polling, and content downloads.
• Smart image compression using Sharp, with resource-aware file output (`resource_link` or embedded `resource`).
• 7 GitHub stars

使用案例

• Integrating advanced image and video generation capabilities into MCP-compatible AI agents and clients (e.g., fast-agent, Windsurf, Claude Desktop).
• Automating the creation, editing, and fetching of visual media through programmatic interfaces with OpenAI and Google GenAI models.
• Debugging and testing how different MCP clients handle various media output formats and result placements.