tavily-search

Web search with LLM-optimized results, content snippets, and relevance scores. Web search returning LLM-optimized results with content snippets and relevance scores. If tvly is not found on PATH, install it first: Do not skip this step or fall back to other tools. See tavily-cli for alternative install methods and auth options. - Supports four search depths (ultra-fast, fast, basic, advanced) with configurable result counts up to 20, plus domain filtering and time-range constraints - Returns structured JSON output with content snippets, relevance scores, and metadata optimized for LLM consumption - Includes specialized search modes for news and finance topics, with optional AI-generated answers and full page content extraction - Integrates into multi-step research workflows: search → extract → map → crawl → research - You need to find information on any topic - You don't have a specific URL yet - First step in the workflow : search → extract → map → crawl → research - Keep queries under 400 characters — think search query, not prompt. - Break complex queries into sub-queries for better results. - Use --include-raw-content when you need full page text (saves a separate extract call). - Use --include-domains to focus on trusted sources.