Claude Code Plugins

Community-maintained marketplace

Feedback

Implement web search, url content extraction, website crawling, and deep research with the tavily API. Use when building agentic workflows, rag systems, or autonomous agents that require real-time context from the web.

Install Skill

1Download skill
2Enable skills in Claude

Open claude.ai/settings/capabilities and find the "Skills" section

3Upload to Claude

Click "Upload skill" and select the downloaded ZIP file

Note: Please verify skill by going through its instructions before using it.

SKILL.md

name tavily-api
description Implement web search, url content extraction, website crawling, and deep research with the tavily API. Use when building agentic workflows, rag systems, or autonomous agents that require real-time context from the web.

Tavily is a specialized search API designed specifically for LLMs, enabling developers to build AI applications that can access real-time, accurate web data. Let's use the Python SDK to build with tavily.

Tavily Python SDK

Installation

pip install tavily-python

Client Initialization

from tavily import TavilyClient

client = TavilyClient(api_key="tvly-YOUR_API_KEY")

# Or use environment variable TAVILY_API_KEY
client = TavilyClient()

Async client:

The async client enables parallel query execution, ideal for agentic workflows that need to gather information quickly before passing it to a model for analysis.

from tavily import AsyncTavilyClient

async_client = AsyncTavilyClient(api_key="tvly-YOUR_API_KEY")

Available Endpoints

Endpoint Purpose Use Case
search() Web search real time data retrieval from the web
extract() Scrape content from URLs Page content extraction
crawl() and map() Traverse website structures and simultaneously scrape pages Documentation, site-wide extraction
research Out of the box research agent ready-to-use iterative research

Choosing the Right Method

If you are building a custom agent or agentic workflow:

Need Method
Web search results search()
Content from specific URLs extract()
Content from an entire site crawl()
URL discovery from a site map()

These methods give you full control but require additional work: data processing, LLM integration, and workflow orchestration.

If you want an out-of-the-box solution:

Need Method
End-to-end research with AI synthesis and built-in context engineering research()

The research endpoint provides faster time-to-value with AI-synthesized insights, but offers less flexibility than building custom workflows.

Detailed Guides

For detailed usage instructions, parameters, patterns, and best practices: