πŸš€ OneSearch : Web Search & Crawl & Scraper & Extract MCP Server

πŸš€ OneSearch MCP Server: Web Search & Scraper & Extract, Support agent-browser, SearXNG, Tavily, DuckDuckGo, Bing, etc.

Remote serverstreamable-httpTypeScript

What is the πŸš€ OneSearch : Web Search & Crawl & Scraper & Extract MCP Server?

πŸš€ OneSearch MCP Server: Web Search & Scraper & Extract, Support agent-browser, SearXNG, Tavily, DuckDuckGo, Bing, etc.

What it actually does

A Model Context Protocol (MCP) server implementation that integrates with multiple search providers for web search, local browser search, URL discovery, and scraping capabilities with agent-browser.

  • Web search, scrape, discover URLs, and preprocess content from websites
  • Support multiple search engines and web scrapers: SearXNG, Tavily, DuckDuckGo, Bing, Google, Zhipu (ζ™Ίθ°±), Exa, Bocha (博ζŸ₯), You.com, etc
  • Local web search β€” (browser search), support multiple search engines: Bing, Google, Baidu, Sogou, etc
  • Use agent-browser for browser automation
  • Free, no API keys required
  • Enabled tools: β€” one_search, one_scrape, one_map, one_extract

Configuration

Browser Requirement: This server uses agent-browser for web scraping and local search, which requires a Chromium-based browser. Good News: The server will automatically detect and use browsers already installed on your system: - βœ… Google Chrome - βœ… Microsoft Edge - βœ… Chromium - βœ… Google Chrome Canary If you don't have any of these browsers installed, you can: ```bash

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

How to install the πŸš€ OneSearch : Web Search & Crawl & Scraper & Extract MCP Server

claude mcp add one-search --env SEARCH_PROVIDER=your-value --env SEARCH_API_URL=your-value --env FIRECRAWL_API_URL=your-value --env FIRECRAWL_API_KEY=your-value --env SEARCH_API_KEY=your-value --env YDC_API_KEY=your-value -- npx -y agent-browser

Configuration

Browser Requirement: This server uses agent-browser for web scraping and local search, which requires a Chromium-based browser. Good News: The server will automatically detect and use browsers already installed on your system: - βœ… Google Chrome - βœ… Microsoft Edge - βœ… Chromium - βœ… Google Chrome Canary If you don't have any of these browsers installed, you can: ```bash

VariableDescriptionRequired
SEARCH_PROVIDERConfiguration value read at startup.Optional
SEARCH_API_URLEndpoint or connection string the server talks to.Yes
FIRECRAWL_API_URLEndpoint or connection string the server talks to.Yes
FIRECRAWL_API_KEYCredential the server authenticates with.Yes
SEARCH_API_KEYCredential the server authenticates with.Yes
YDC_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • β€œUse πŸš€ OneSearch : Web Search & Crawl & Scraper & Extract to Cursor.”
  • β€œUse πŸš€ OneSearch : Web Search & Crawl & Scraper & Extract to Windsurf.”

Frequently asked questions

The server supports `searxng`, `duckduckgo`, `bing`, `tavily`, `google`, `zhipu`, `exa`, `bocha`, and `local` (browser-based). Default is `local`.