vision-mcp

weekitmo/vision-mcp

★ 0 stars Python AI/LLM Updated 3d ago

MCP server for image understanding through OpenAI-compatible vision APIs. To provide image recognition capabilities for those large models that do not support Multimodal.

View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "vision-mcp": {
      "command": "uvx",
      "args": [
        "vision-mcp"
      ]
    }
  }
}

Or install with pip: pip install vision-mcp

README Excerpt

<p align="center"> <h1 align="center">Vision MCP</h1> </p> <p align="center"> <strong>Give text-only agents vision through any OpenAI-compatible provider.</strong> </p> <p align="center"> <a href="https://github.com/weekitmo/vision-mcp"><img src="https://img.shields.io/badge/MCP-Image%20Understanding-222222" alt="MCP Image Understanding"></a>

Tools (5)

VISION_API_KEYVISION_BASE_URLVISION_MODELVISION_TIMEOUTanalyze_image

vision-mcp

Quick Install

README Excerpt

Tools (5)

Related AI/LLM Servers