---
title: Tavily connector
description: Use the Tavily connector to search the web for current information and extract content from web pages using the Tavily API.
url: https://docs-v3-preview.elastic.dev/elastic/kibana/pull/280898/reference/connectors-kibana/tavily-action-type
products:
  - Kibana
applies_to:
  - Elastic Cloud Serverless: Preview
  - Elastic Stack: Preview since 9.4
---

# Tavily connector
The Tavily connector uses the [Tavily API](https://docs.tavily.com) to search the web for current information and extract content from web pages. It connects using Tavily's hosted MCP server.

## Create connectors in Kibana

You can create connectors in **Stack Management > Connectors**.

### Connector configuration

Tavily connectors have the following configuration properties:
<definitions>
  <definition term="API Key">
    The Tavily API key for authentication. This is a bearer token that starts with `tvly-`.
  </definition>
</definitions>


## Test connectors

You can test connectors when you create or edit the connector in Kibana.
The Tavily connector has the following actions:
<definitions>
  <definition term="Search">
    Search the web for current information on any topic.
    - `query` (required): The search query to execute.
    - `max_results` (optional): Maximum number of results to return. Defaults to 10.
    - `search_depth` (optional): `basic`, `advanced`, `fast`, or `ultra-fast`. Advanced returns more thorough results; fast and ultra-fast optimize for lower latency.
    - `topic` (optional): Search category — `general`.
    - `include_images` (optional): Whether to include images in the response. Defaults to false.
  </definition>
  <definition term="Extract">
    Extract and retrieve content from one or more web page URLs.
    - `urls` (required): List of URLs to extract content from.
    - `extract_depth` (optional): Depth of extraction — `basic` or `advanced`. Use advanced for LinkedIn, protected sites, or tables.
    - `include_images` (optional): Whether to include images extracted from the pages. Defaults to false.
  </definition>
  <definition term="Crawl">
    Crawl a website starting from a URL, extracting content from pages with configurable depth and breadth.
    - `url` (required): The root URL to begin the crawl.
    - `max_depth` (optional): Maximum depth of the crawl. Defaults to 1.
    - `max_breadth` (optional): Maximum number of links to follow per page. Defaults to 20.
    - `limit` (optional): Total number of links to process before stopping. Defaults to 50.
    - `instructions` (optional): Natural language instructions specifying which types of pages to return.
    - `extract_depth` (optional): `basic` or `advanced`. Defaults to basic.
  </definition>
  <definition term="Map">
    Map a website's structure by returning a list of URLs found starting from a base URL.
    - `url` (required): The root URL to begin the mapping.
    - `max_depth` (optional): Maximum depth of the mapping. Defaults to 1.
    - `max_breadth` (optional): Maximum number of links to follow per page. Defaults to 20.
    - `limit` (optional): Total number of links to process before stopping. Defaults to 50.
    - `instructions` (optional): Natural language instructions for the crawler.
  </definition>
</definitions>


## Connector networking configuration

Use the [Action configuration settings](/elastic/kibana/pull/280898/reference/configuration-reference/alerting-settings#action-settings) to customize connector networking, such as proxies, certificates, or TLS settings. You can set configurations that apply to all your connectors or use `xpack.actions.customHostSettings` to set per-host configurations.

## Get API credentials

To use the Tavily connector:
1. Create a free account at [tavily.com](https://tavily.com).
2. Go to the [API Keys](https://app.tavily.com/home) page in the Tavily dashboard.
3. Copy your API key (starts with `tvly-`).
4. Enter the API key in the **API Key** field when configuring the Tavily connector in Kibana.