AI Agent Hub
Back to plugins
🤖

dsh-qwen-mm

Model Inference Updated 2026.08.15

Run the following command in DeepSeek Harness:

dsh plugin install RRRosmontis/dsh-qwen-mm

Paste the following prompt into your AI chat to install this plugin:

Run dsh plugin install RRRosmontis/dsh-qwen-mm (source: https://github.com/RRRosmontis/dsh-qwen-mm) in your DeepSeek Harness terminal, then restart with dsh --profile web to make all MCP tools available in your session.

About this plugin

DeepSeek Harness runs text-only models that cannot natively read images, video, or documents. dsh-qwen-mm bridges the full Qwen-MM-Plugins toolchain into Harness via MCP, giving the same model access to read_image, vision_chat, web_search, video-edit, blender, and more. Capabilities span local file parsing (no API key needed), cloud OCR/ASR via DashScope, image-based search, long-video Q&A, Blender/FreeCAD 3D modeling, and math-education video generation. This plugin is ideal for developers and researchers who want multimodal reading, content creation, and 3D-assisted design within a single DeepSeek session without switching to a different model.

Use Cases

  • Drag a product image into a DeepSeek chat and let the model read and describe it
  • Upload a technical demo video for long-video Q&A and editing via MCP tools
  • Invoke Blender or FreeCAD tools for 3D modeling and CAD design assistance

Best For

  • Developers adding multimodal capabilities to existing DeepSeek workflows
  • Researchers handling mixed image-text Q&A with text models
  • Engineers doing 3D/CAD-assisted design via the MCP toolchain