[email protected]

noapi-google-mcp 또는 gpt-oss-20B/120B-Vision 등 파이프라인 중인 다른 오픈 소스 모델을 지원하고 싶으시다면, 제 GPU 컴퓨트 자금에 추가해 주세요: 약 3000달러가 필요합니다.

이 정보가 유용하다면 지속적인 개발과 새로운 기능 지원을 고려해 주세요. BTC: 16DT4AHemLyn7C6P116YepjY518gu9wUUH ETH: 0x7287D1F9c77832cFF246937af0443622bFdACD04

38개의 도구. API 키는 전혀 없습니다. 로컬 LLM에 실제 구글 검색, 실시간 피드, 비전, OCR, 그리고 완전한 영상 이해를 제공합니다.

로컬 LLM을 완전히 연결된 어시스턴트로 바꾸는 MCP 서버입니다. 실제 구글 결과, 실시간 뉴스 및 소셜 피드, 역이미지 검색, 오프라인 OCR, 유튜브 전사, 클립 추출 — 모두 헤드리스 크로미엄과 오픈 소스 ML 모델을 통해 로컬에서 실행됩니다. API 키, 사용 제한, 클라우드 의존도 없습니다.

LM Studio, Claude Desktop, OpenClaw, Ollama 및 모든 MCP 호환 클라이언트에서 작동합니다.

---

v0.3.1의 새로운 소식 — 안티봇 탐지 및 신경망 캡차(CAPTCHA) 해석기

구글은 헤드리스 크롬 브라우저를 포착해 검색 결과 (#2) 대신 캡차를 제공하기 시작했습니다.

noapi-google-search-mcp

[email protected]

If you want to support noapi-google-mcp or gpt-oss-20B/120B-Vision and other open source models in the pipeline please add to my GPU compute fund: around $3000 are needed.

If you find this useful, consider supporting continued development and new features.BTC: 16DT4AHemLyn7C6P116YepjY518gu9wUUH ETH: 0x7287D1F9c77832cFF246937af0443622bFdACD04

38 tools. Zero API keys. Give any local LLM real Google search, live feeds, vision, OCR, and full video understanding.

An MCP server that turns your local LLM into a fully connected assistant. Real Google results, live news and social feeds, reverse image search, offline OCR, YouTube transcription and clip extraction — all running locally through headless Chromium and open-source ML models. No API keys, no usage limits, no cloud dependency.

Works with LM Studio, Claude Desktop, OpenClaw, Ollama, and any MCP-compatible client.

---

What’s New in v0.3.1 — Anti-Bot Detection & Neural Net CAPTCHA Solver

Google started catching headless Chromium browsers and serving CAPTCHAs instead of search results (#2). Fixed it properly and then added a neural net CAPTCHA solver just for the hell of it.

Stealth patches:

• JavaScript injection before every page load patches navigator.webdriver, fake browser plugins, chrome.runtime, and removes Playwright fingerprints
• Fixed User-Agent mismatch (was aarch64, now matches the actual Chromium binary)
• Cookie persistence between sessions so Google sees a returning browser, not a fresh bot
• Human-like random delays between page interactions
• Clear error messages when rate-limited instead of cryptic timeouts

Neural net CAPTCHA solver (MobileNetV2 + OpenCV):

• When Google serves a reCAPTCHA image challenge (“Select all images with traffic lights”), the server now attempts to solve it automatically
• Uses MobileNetV2 (ImageNet classifier, ~13MB ONNX model, auto-downloads on first encounter)
• OpenCV splits the CAPTCHA grid into cells, each cell is classified by the neural net and matched against the prompt
• Covers 22 common CAPTCHA categories: traffic lights, buses, bicycles, motorcycles, cars, bridges, boats, trains, trucks, fire hydrants, parking meters, tractors, and more
• Human-like mouse movement for clicking cells and the verify button
• Falls back gracefully if the challenge type isn’t supported

Will it solve every CAPTCHA? No. But it’ll get through some of them, and honestly we mostly built it because we could.

---

What’s New in v0.3.0 — 16 New Tools

YouTube RAG — Subscribe, Transcribe, Search, Clip