tavily-search
Tavily Search queries the entire web and returns ranked results with relevance scores and optional AI-generated answers in one call. Unlike single-URL fetching, it powers research workflows, competitive analysis, and "what's the latest" questions with configurable search depth, time ranges, and content extraction across multiple pages.
Tavily Search lets you query the web and receive AI-generated answers with ranked, scored results in a single API call.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-28
Tavily Search lets you query the web and receive AI-generated answers with ranked, scored results in a single API call. Tavily Search queries the entire web and returns ranked results with relevance scores and optional AI-generated answers in one call. Unlike single-URL fetching, it powers research workflows, competitive analysis, and "what's the latest" questions with configurable search depth, time ranges, and content extraction across multiple pages.
Use it when
- Yes.
- Tavily Search lets you query for the latest AI news by specifying your topic and configurable time ranges.
Verify before relying
Read SKILL.md below before installing (1 file). Open directory: indexed for reading, not audited.
Install
xg-gh-25/SwarmAI/s_tavily-search · repository language: Python
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What does tavily-search do?
Tavily Search queries the entire web and returns ranked results with relevance scores and optional AI-generated answers in one call. Unlike single-URL fetching, it powers research workflows, competitive analysis, and "what's the latest" questions with configurable search depth, time ranges, and content extraction across multiple pages.
Can tavily-search extract content from multiple URLs?
Yes. Tavily Search supports batch extraction of full content from multiple URLs, enabling workflows that need to gather and process information across several web pages in a single operation rather than fetching them one at a time.
How do I search the web for latest AI news using tavily-search?
Tavily Search lets you query for the latest AI news by specifying your topic and configurable time ranges. The skill returns ranked results with relevance scores and can optionally generate AI-powered answers, helping you stay current on breaking developments.
Does tavily-search support region-specific or domain-filtered searches?
Yes. Tavily Search offers research capabilities with region-specific and domain-filtered search options, allowing you to narrow results by geography or restrict searches to particular websites when you need targeted information.
What is tavily-search licensed under?
Tavily Search is licensed under the MIT license, making it freely available for use, modification, and distribution in both open-source and commercial projects.
Can other skills use tavily-search for web search?
Yes. Tavily Search is designed to power other skills with web search and content retrieval capabilities, enabling downstream applications to access ranked web results and extracted content as part of their workflows.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Tavily Search
Why? WebFetch can only grab a single known URL. Tavily searches the entire web, returns ranked results with relevance scores, and can generate AI-powered answers -- all in one API call. Essential for answering "what's the latest on X?" or powering research workflows.
Quick Start
"Search the web for latest AI agent frameworks"
"What's the latest news about OpenAI?"
"Extract the main content from these 5 URLs"
Setup
Requires TAVILY_API_KEY environment variable.
# Check if set
echo $TAVILY_API_KEY
# If not, set it (get key from https://app.tavily.com)
export TAVILY_API_KEY=tvly-your-key-here
Free tier: 1,000 API credits/month. Basic search = 1 credit. Advanced search = 2 credits.
API Reference
Search
POST https://api.tavily.com/search
```bash curl -s -X POST https://api.tavily.com/search \
(truncated - see the full file via the links below)
File tree — 1 file
backend/skills/s_tavily-search/SKILL.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Search the web and get AI-powered answers with ranked results”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Tavily wraps the Tavily REST API to enable web search, content extraction, site discovery, and crawling directly from your agent. It returns structured results with titles, URLs, and summaries designed for downstream LLM use, and supports optional research workflows with citations when deeper investigation is needed.
Query the web and retrieve ranked results optimized for language models using Tavily's search API. Configure search depth, time ranges, domain filters, and result limits to fit your agent's needs. Supports OAuth or API key authentication with no manual setup required.
Tavily is an AI-optimized search engine built for language model applications that need current web data. It provides web search, URL content extraction, site crawling, and autonomous research capabilities—all designed to return results formatted for LLM consumption rather than human browsing.
Tavily provides a web search API purpose-built for AI agents, returning organized results that LLMs can consume directly. It supports both quick and deep search modes, with configurable result limits and domain filtering to suit different research needs.
Tavily Extract retrieves and converts web page content into clean markdown or text format from URLs you specify. Supports batch processing up to 20 URLs per request, with options for query-focused extraction and handling of JavaScript-rendered pages.
Web-search-tavily delivers AI-driven search and research through multiple specialized endpoints: execute targeted queries with configurable depth and relevance tuning, extract and parse content from specific URLs, crawl entire websites as graphs, or launch comprehensive research tasks that synthesize multiple sources into detailed reports. Choose between fast, balanced, or advanced search modes depending on your latency and precision needs.
More skills Tavily (NOASSERTION) · tavily-research (MIT) · tavily-web (MIT) · Tool Serper检索 (unlicensed) · Web Search Plus (MIT)