Show HN: I taught GPT-OSS-120B to see using Google Lens and OpenCV

Source: Hacker News

Overview

I built an MCP server that gives any local LLM real Google search and vision capabilities—no API keys needed. The latest feature, google_lens_detect, uses OpenCV to find objects in an image, crops each one, and sends them to Google Lens for identification. GPT‑OSS‑120B, a text‑only model with zero vision support, correctly identified an NVIDIA DGX Spark and a SanDisk USB drive from a desk photo.

Features

• Google Search, News, Shopping, Scholar, Maps, Finance, Weather, Flights, Hotels, Translate, Images, Trends, and more (17 tools total)
• Vision support via OpenCV + Google Lens (google_lens_detect)
• No API keys required

Installation

pip install noapi-google-search-mcp
playwright install chromium

Links

• GitHub: https://github.com/VincentKaufmann/noapi-google-search-mcp
• PyPI: https://pypi.org/project/noapi-google-search-mcp/