Generative-Media-Skills

Generative-Media-Skills

Multimodal generative media skills, supporting high-quality image, video, and audio generation.

MCPDesignOpen source多模态生成媒体AI 代理
Type
MCP
Transport
stdio
Open source
Yes
GitHub Stars
★ 3.6k
Source
mcp-github

Overview

Generative-Media-Skills is a multimodal generative media skill library designed for AI agents (such as Claude Code, Cursor, and Gemini CLI). It provides high-quality image, video, and audio generation capabilities via muapi.ai. The skill library includes various tools and preset workflows, enabling AI agents to generate, edit, and display professional-grade multimedia content. Ideal for developers and teams requiring multimedia generation capabilities.

Capabilities

  • High-quality image generation
  • Video generation and editing
  • Audio generation
  • Local file upload support
  • Direct media rendering
  • Access to 100+ AI models

Use cases

Generate cinematic-quality videosCreate brand logosProduce animated short filmsGenerate product showcase videos

Setup

Requires: API KeyNode 环境
Run `muapi mcp serve` to start the MCP server and connect to Claude Desktop, Cursor, or other MCP-compatible agents.

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

How do I get started with Generative-Media-Skills?

Refer to the quick start guide in the README.

Which AI models are supported?

Supports over 100 models including Midjourney v7, Flux Kontext, Seedance 2.0, and more.

Related skills