Free Search
Local-first, multi-engine web search, fetch, and document reading with no API keys required.
Free Search is a local-first MCP server for web search, page fetching, and document reading that requires no external API keys. It queries multiple search engines including DuckDuckGo, Mojeek, and Startpage with automatic Playwright fallback, extracts readable content, parses PDF/DOCX/HTML/Markdown documents, and caches results in a full-text searchable local index.
Source
Repository: https://github.com/sweetcornna/free-search-mcp
Maintain Free Search?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[Free Search on getagentictools](https://getagentictools.com/mcp/sweetcornna-free-search-mcp?ref=badge) Related mcp
ScreenHand Native desktop control for MCP agents.
Scrapfly Enterprise web scraping with built-in anti-bot handling and proxy rotation
System Bridge Provides native OS functionality for opening URLs in the default browser, copying text to the clipboard, and retrieving detailed c
TUI Interact with terminal user interface applications through managed pseudo-terminals with session management, screenshots, text rea
Playwright Scraper Leverages Playwright and BeautifulSoup to enable robust web scraping and content extraction, converting complex JavaScript-heavy w
Tencent IMA Manage knowledge bases on Tencent IMA with 40+ tools for CRUD operations, web content extraction, tag management, and AI-powered s