vision-mcp

mahonzhan/vision-mcp

★ 0 stars Go 🤖 AI/LLM Updated 4d ago

Give text-only LLMs the power to "see" local images. A secure, high-performance Go implementation of MCP Server utilizing external Vision APIs.

View on GitHub → Try with Claude — $10 free →

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": "go",
      "args": [
        "run",
        "github.com/mahonzhan/vision-mcp@latest"
      ]
    }
  }
}

README Excerpt

A high-performance, secure **Model Context Protocol (MCP)** server written in Go that empowers text-only Large Language Models (such as DeepSeek-V4, GLM-5.1 or other text-only models) to "see" and analyze local image files by calling an external OpenAI or OpenAI-compatible Vision Model. --- This MCP server is **specifically designed for text-only Large Language Models** that do not natively support image inputs (multimodality).

Tools (3)

OPENAI_API_KEYOPENAI_BASE_URLOPENAI_DEFAULT_MODEL

vision-mcp

Quick Install

README Excerpt

Tools (3)

Related AI/LLM Servers