llm-openai-vision-mcp

Hilderin/llm-openai-vision-mcp
★ 0 stars Python 🤖 AI/LLM Updated today
Give your AI eyes - an MCP server that lets agents visually inspect images via OpenAI's vision API, with pass/fail verdicts against your criteria.
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": {
    "llm-openai-vision-mc": {
      "command": "uvx",
      "args": [
        "llm-openai-vision-mcp"
      ]
    }
  }
}

Or install with pip: pip install llm-openai-vision-mcp

README Excerpt

Local MCP server for analyzing images using the OpenAI vision API. Designed for OpenCode agents to inspect screenshots, diagrams, UI renders, and other visual assets during development. The server exposes an MCP tool so agents can submit an image file path along with acceptance criteria and get back a detailed vision-based analysis — all locally, no external services beyond the OpenAI API.

Tools (5)

acceptance_criteriaanalyze_imageexpectedknown_tolerancespath