tavily-search
Installation
Summary
Web search with LLM-optimized results, content snippets, and relevance scores.
- 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
SKILL.md
Tavily search
Use the tavily_search, tavily_extract, tavily_map and tavily_crawl tools if your tool list has them
(some clients add a prefix such as mcp__tavily__). Otherwise run tvly <command> directly; there's no
need to check for it first. If neither works, follow setup.
Parameters are named as in the API (max_results). The CLI spells them as flags (--max-results) with
comma-separated lists (--include-domains sec.gov,reuters.com). For exact parameters, read the tool schema,
run tvly <command> --help, or see the API reference.
| You have | You need | Use |
|---|---|---|
| A question or topic | Sources, facts or news | Search |
| URLs | Their content | Extract |
| A site, not the exact page | The right page's URL | Map |
| A site section | Many of its pages | Crawl |