Build production-ready Tavily integrations with best practices baked in. Reference documentation for developers using coding assistants (Claude Code, Cursor, etc.) to implement web search, content extraction, crawling, and research in agentic workflows, RAG systems, or autonomous agents.
Install and authenticate the Tavily CLI (tvly) in a coding-agent terminal. Use only when the user asks to install tvly, run tvly login, or check CLI status, or when a terminal session has no callable Tavily MCP tools. Not for ordinary web search, extraction, mapping, crawling, or research.
Collect content from many pages on the same site. Use when the user wants to crawl, download docs, extract a whole section such as /docs, bulk-extract pages, or says "get all the pages" or "extract everything under".
Extract clean content from known URLs. Use when the user supplies one or more URLs and wants the page text, says "extract", "grab the content from", "pull the text from", "get the page at", or "read this webpage".
Produce cited multi-source research. Use when the user wants a deep report, comparison, market analysis, or literature review, or says "research", "investigate", "analyze in depth", "compare X vs Y", or "what does the market look like for". For a quick fact, use tavily-search instead.
Search the web for current sources and snippets. Use when the user wants to search, look up, find articles, get recent news, or discover sources, and does not already have a URL. Triggers: "search for", "look up", "find me", "what's the latest on", "find articles about".
Discover URLs on a known website without extracting page content. Use when the user wants the site structure, to find a specific page on a large site, or says "map the site", "list the pages", "what URLs are on", or "find the docs URL".
★not rated 2 5d agoA60 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: