vision-mcp

white-drizzle/vision-mcp

★ 0 stars Python AI/LLM Updated today

MCP server that gives vision-less LLMs (DeepSeek) image understanding via Volcengine Agent Plan multimodal models

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

Give vision-less main models (like DeepSeek) the ability to **see images**, powered by Volcano Engine (Volcengine) Agent Plan's multimodal model through an OpenAI-compatible endpoint. 为无视觉主模型（如 DeepSeek）补上**读图能力**。后端视觉模型走火山引擎（Volcengine）Agent Plan 的多模态模型，OpenAI 兼容端点。 - **Image analysis** — local path / URL / base64 / data URL

Tools (6)

analyze_htmlanalyze_imageanalyze_pptcheck_ppt_overlapdescribe_imagemcpServers

vision-mcp

Quick Install

README Excerpt

Tools (6)

Related AI/LLM Servers