uk0

uk0 / web-search-fast

Public

一个简单的本地 web search mcp ，可以集群规模化进行对外提供服务。

19
1
89% credibility
Found Feb 18, 2026 at 15 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

A service that performs web searches on major engines using stealth browsers to return structured JSON or Markdown results, with an admin dashboard for monitoring and API key management.

How It Works

1
🔍 Discover the web searcher

You hear about a handy tool that grabs fresh search results from the web without getting blocked, perfect for getting up-to-date info.

2
📥 Bring it home

Download the ready-to-use package and follow a few easy steps to set it up on your computer.

3
🚀 Turn it on

Hit start, and your personal search helper comes alive, ready to fetch results anytime.

4
Pick your way to search
📱
Quick direct search

Type a question and get clean results in neat lists or easy-to-read notes.

🤖
Team up with AI

Link it to your AI assistant so it can pull real-time facts during chats.

5
📊 Check the dashboard

Peek at your search history, create private passes, or block pesky visitors if needed.

🎉 Fresh info at your fingertips

Enjoy reliable, detailed web results every time, keeping you informed without hassle.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 15 to 19 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is web-search-fast?

This Python-based FastAPI service delivers a fast web search engine by scraping Google, Bing, or DuckDuckGo SERPs with a stealth Camoufox browser that dodges detection. It pulls structured results in JSON or Markdown, with optional depth crawling for page content or sub-links, solving the pain of unreliable public search APIs or brittle scrapers. Run it locally as a web search API on port 8000 or as an MCP server for Claude tools like web_search and get_page_content.

Why is it gaining traction?

Its cave browser fast web search stands out with automatic engine fallback (Google blocks? Switch to DDG), concurrency via browser pooling, and a built-in admin UI for API keys, search logs, and IP bans—perfect for production without extra setup. Docker and Nuitka builds make it the fastest web search for self-hosted setups, while MCP integration hooks into Grok or Claude for real-time AI lookups. Devs love the zero-config curl-friendly endpoints and live tests.

Who should use this?

Backend devs building apps needing a reliable fast web search API without vendor lock-in, like custom dashboards or chatbots. AI engineers integrating live web data into Claude or similar via MCP tools for up-to-date facts. Teams scraping GitHub projects or running fast people search web without proxy hassles.

Verdict

Solid early project with excellent docs, Docker support, and 26+ tests—grab it if you need a fastest web search engine locally, but with only 15 stars and 0.9% credibility score, test thoroughly before prod. Promising for fastmcp web search in AI workflows.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.