loading…
Search for a command to run...
loading…
A local vision-language MCP server that enables Claude Code to perform image analysis, OCR, and UI-to-code generation using the Qwen3 VL 4B model via LM Studio.
A local vision-language MCP server that enables Claude Code to perform image analysis, OCR, and UI-to-code generation using the Qwen3 VL 4B model via LM Studio. It provides privacy-focused visual processing by running entirely on the user's local hardware without external API dependencies.
English Installation | 中文安装 | 中文 README
A vision-language MCP server that enables Claude Code to analyze images using Qwen3 VL 4B model running locally via LM Studio.
git clone https://github.com/hydroCoderClaud/mcp-hydrocoder-vision.git
cd mcp-hydrocoder-vision
npm install
npm run build
Qwen3-VL-4B-Instruct modelhttp://localhost:1234)Add to your ~/.claude/settings.json:
{
"mcpServers": {
"hydrocoder-vision": {
"command": "npx",
"args": ["-y", "mcp-hydrocoder-vision"],
"env": {
"LM_STUDIO_URL": "http://localhost:1234/v1/chat/completions",
"VISION_MODEL": "Qwen3-VL-4B-Instruct"
}
}
}
}
analyzeImageAnalyze an image and get a detailed description.
/analyzeImage imagePath: "C:/path/to/image.png" prompt: "What's in this image?"
extractTextExtract text from an image (OCR).
/extractText imagePath: "C:/path/to/document.png" language: "English"
describeForCodeGenerate code from a UI/design screenshot.
/describeForCode imagePath: "C:/path/to/design.png" framework: "Vue"
| Variable | Default | Description |
|---|---|---|
LM_STUDIO_URL |
http://localhost:1234/v1/chat/completions |
LM Studio API endpoint |
VISION_MODEL |
Qwen3-VL-4B-Instruct |
Model name to use |
# Run in development mode (watch mode)
npm run dev
# Build for production
npm run build
# Start the built server
npm start
LM_STUDIO_URL is correctMIT
Добавь это в claude_desktop_config.json и перезапусти Claude Desktop.
{
"mcpServers": {
"mcp-hydrocoder-vision": {
"command": "npx",
"args": []
}
}
}