Qwen-MM-Plugins
Make any agent harness multimodal-native.
Qwen-MM-Plugins delivers native multimodal capabilities to AI coding assistants through installable skills and optional MCP servers. Built by the Qwen team, it enables agents to process images, video, audio, documents, 3D models, medical imaging (NIfTI), and more through eight specialized capability modules. Each capability—ranging from core media reading to Blender 3D workflows—installs independently and integrates with Claude Code, Qwen Code, Codex, and other harnesses. Developers can reference files directly in chat prompts, letting the skills automatically invoke the appropriate tools for tasks like video transcription, PDF table extraction, or parametric CAD modeling.
Key Features
Use Cases
- 01Summarizing specific pages in PDF reports and extracting embedded tables or charts
- 02Transcribing video meetings with speaker labels and accurate timestamps
- 03Reverse-searching images to identify photo locations and verifying details on the web
- 04Analyzing two-hour lecture videos to generate timestamped outlines of main topics
- 05Inspecting medical NIfTI brain scans with metadata and orthogonal center-slice visualization
- 06Automating 3D modeling, lighting, texturing, and rendering workflows in Blender through natural language
Related Skills
View moresuperpowers
An agentic skills framework & software development methodology that works.
skills
Skills for Real Engineers. Straight from my .agents directory.
skills
Public repository for Agent Skills
ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Qwen-MM-Plugins — FAQ
What is Qwen-MM-Plugins?+
Qwen-MM-Plugins is a suite of agent skills and optional MCP servers that add multimodal processing—images, video, audio, documents, 3D models, and medical imaging—to AI coding assistants like Claude Code, Qwen Code, and Codex. Each of the eight capabilities installs independently to enable specific workflows.
How do I install Qwen-MM-Plugins?+
Run the guided installer via curl for Claude Code, Codex, Qwen Code, and similar harnesses: curl -fsSL https://raw.githubusercontent.com/QwenLM/Qwen-MM-Plugins/main/install.sh | bash. For WorkBuddy, QoderWork, QwenWork, DeepSeek Harness, Hermes Agent, and others, consult the manual harness setup guide in the repository.
Which AI clients work with Qwen-MM-Plugins?+
The guided installer supports Claude Code, CodeBuddy, Codex, Qoder, OpenClaw, Qwen Code, and Gemini CLI. Manual in-app setup is available for WorkBuddy, QoderWork, and QwenWork, with documented procedures for DeepSeek Harness, Hermes Agent, opencode, pi, and QwenPaw.
Do I need API keys to use Qwen-MM-Plugins?+
The core capability requires no API key for native image reading. The api capability (Qwen VL/Omni vision, OCR, ASR, segmentation) requires a DashScope key, search needs Serper/Exa/Tavily, and video-memory and video-edit both depend on DashScope.
What are the system prerequisites for Qwen-MM-Plugins?+
You need uv (for uvx) to install Python dependencies on demand. Audio/video workflows require ffmpeg, Blender/FreeCAD capabilities need their respective applications, and headless Linux servers need Xvfb. NIfTI support requires the nibabel library.
Is Qwen-MM-Plugins free and open source?+
Yes, Qwen-MM-Plugins is released under the Apache-2.0 license and is fully open source. Third-party components in the Blender and FreeCAD integrations are documented in their respective NOTICE files.
How do I install Qwen-MM-Plugins?+
Open the source repository on GitHub and follow its README. Qwen-MM-Plugins is a skill — MCP Agents Market links you directly to the official repo.
Is Qwen-MM-Plugins free?+
Qwen-MM-Plugins is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.