> ## Documentation Index
> Fetch the complete documentation index at: https://docs.boostgpt.co/llms.txt
> Use this file to discover all available pages before exploring further.

# Tavily

> Search, extract and crawl, built for agents. A second reader for when Firecrawl is blocked.

Search, extract and crawl, built for agents. A second reader for when Firecrawl is blocked.

## Connecting

In the dashboard, open **Connectors**, find Tavily and press **Connect**. The key you enter is checked against Tavily before anything is saved, so a key that is refused never becomes a connection that fails later.

### What you will need

| Field   | What it is          |
| ------- | ------------------- |
| API Key | Your Tavily API key |

### Getting the credential

1. Create an API key at [app.tavily.com](https://app.tavily.com) — it starts with `tvly-`
2. Paste it into the connector

## Notes

* `include_answer` makes Tavily write a direct answer alongside the sources — useful when the agent just needs
  the fact rather than the pages.
* `search_depth: advanced` costs more credits and finds more; leave it `basic` for routine lookups.
* `map` is much cheaper than `crawl` when you only need to know what exists on a site.

## What an agent can do with it

| Tool      | What it does                                                                                                                                           |
| --------- | ------------------------------------------------------------------------------------------------------------------------------------------------------ |
| `search`  | Search the web and get results already summarised for an agent. Set include\_answer to have Tavily write a direct answer as well as returning sources. |
| `extract` | Pull the readable content out of specific URLs, without searching.                                                                                     |
| `crawl`   | Follow links from a starting URL and return the content of the pages found.                                                                            |
| `map`     | List the URLs on a site without fetching their content. Cheap way to see structure.                                                                    |

## Useful resources

* [Tavily documentation](https://docs.tavily.com)