dsh-qwen-mm
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
Related Plugins
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.
An armor-breaking plugin for DeepSeek: rewrites instruction priority, expands refusal-blocked phrases, persists across sessions, and shows a green active indicator.