by yokingma · MCP Server · ★ 103
π OneSearch MCP Server: Web Search & Crawl & Scraper & Content Prep A Model Context Protocol (MCP) server implementation that integrates with multiple search providers for web search, local browser search, and scraping capabilities with agent-browser. Features Web search, scrape, crawl and preprocess content from websites. Support multiple search engines and web scrapers: SearXNG, Tavily, DuckDuckGo, Bing, Google, Zhipu (ζΊθ°±), Exa, Bocha (εζ₯), etc. Local web search (browser search), support multiple search engines: Bing, Google, Baidu, Sogou, etc. Use for browser automation.
| Stars | 103 |
| Forks | 18 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 64.486/100 |
| Open Issues | 2 |
| Last Updated | 2026-04-16 |
| Created | 2025-03-18 |
| Platforms | browser, mcp, node |
| Est. Tokens | ~26k |
These tools work well together with one-search-mcp for enhanced workflows:
Explore other popular mcp server tools:
one-search-mcp is π OneSearch MCP Server: Web Search & Scraper & Extract, Support agent-browser, SearXNG, Tavily, DuckDuckGo, Bing, etc.. It is categorized as a MCP Server with 103 GitHub stars.
one-search-mcp is primarily written in TypeScript. It covers topics such as agent-browser, bing-mcp, duckduckgo-mcp.
You can find installation instructions and usage details in the one-search-mcp GitHub repository at github.com/yokingma/one-search-mcp. The project has 103 stars and 18 forks, indicating an active community.
one-search-mcp is released under the MIT license, making it free to use and modify according to the license terms.