jugglework-vision-mcp

Level CLocal

Multi-provider vision MCP server for image recognition (OCR, scene description, chart extraction). Supports Qwen-VL, OpenAI, Gemini, Claude, OpenRouter, Ollama and any OpenAI-compatible endpoint.

⭐ 6 · Parent repoDevelopment ToolsTypeScriptRepo ↗Updated 2026-11-19

Installation

MCP client config (paste into mcp.json)

{
  "mcpServers": {
    "juggleai-jugglework-desktop-packages-jugglework-vision-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "jugglework-vision-mcp"
      ]
    }
  }
}

Agent install prompt

Copy and paste into Cursor / Claude / other agents to install this MCP for you

Please read this MCP repository and install it into my current environment:
https://github.com/juggleai/jugglework-desktop/tree/main/packages/jugglework-vision-mcp

Known working client config (can write into mcp.json):
{
  "mcpServers": {
    "juggleai-jugglework-desktop-packages-jugglework-vision-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "jugglework-vision-mcp"
      ]
    }
  }
}

Please: 1) check README for deps and env vars; 2) write config for my client; 3) if secrets are missing, tell me what to fill — do not invent values.

Related servers