Back to News
Alibaba Qwen•August 4, 2026
Qwen-MM-Plugins
Open Source
multimodal
ai-agents
mcp
open-source
### TL;DR
Qwen-MM-Plugins is an open-source collection of multimodal skills and Model Context Protocol (MCP) servers designed to make various AI agent harnesses natively multimodal. It enables agents to perform complex tasks such as long-video analysis, 3D modeling in Blender, parametric CAD in FreeCAD, and media generation without requiring a custom runtime.
Key Insights & Metrics
Pricing
Free and open-source (Apache-2.0 license); requires external API keys (DashScope, Serper) for specific hosted functions.
Cost structure
Version
1.0.0
Current release version
Hardware
Linux or WSL2 on Windows; requires system tools like ffmpeg, and optional software like Blender, FreeCAD, LibreOffice, or Chromium depending on the chosen capability
Compute requirements
Category
Open Source
Licensing model
Region
China
Primary region
Key Features
- Modular capability architecture using skills and MCP servers
- Support for six major agent harnesses including Claude Code, Qwen Code, and OpenClaw
- Advanced vision and media tools: OCR, grounding, segmentation, and long-video memory
- Direct integration with professional software: Blender (3D modeling) and FreeCAD (parametric CAD)
- Dynamic-resolution processing for images, videos, and documents
- Unified configuration management via a shared local config file
Discussion
0
Upvotes
0
Downvotes
0 reviews
Sign in to leave a review
Reviews
No reviews yet. Be the first to review!