# Tavily (Official Partner)

## Tavily (Official Partner)

This guide helps you connect Tavily to your AI Worker. Tavily provides real-time web search, data extraction, and web mapping capabilities. Once connected, your AI Worker can access live information from the web instead of relying on training data alone.

1. Sign up for a Tavily account and get your API key at [app.tavily.com/home](https://app.tavily.com/home).
2. In Toolhouse, open the [Workers](https://toolhouse.app/agents) page and click on the Worker you want to connect Tavily to.
3. In the top menu, click **Details**.

   ![](/files/OhdTDAXpMvvv2pVD2rCQ)
4. Open the **MCP Servers** section.
5. Paste your Tavily MCP URL into the input field, replacing `<your-api-key>` with the key from step 1:

   ```
   https://mcp.tavily.com/mcp/?tavilyApiKey=<your-api-key>
   ```
6. Click **Add Server**, then **Save**. Tavily is now connected to your Worker.

### Testing your Worker

Open the Testing Workbench for your Worker and try a web search request. For example:

> What are the latest news headlines about AI today?

Your Worker should return live, sourced results from the web. If it does, Tavily is working correctly.

### Next steps

With Tavily connected, your Worker can now support use cases like:

* **Real-time research** — look up current news, company information, or market trends
* **Due diligence** — verify claims and research individuals or organizations against live web data
* **Content intelligence** — extract structured information from news sources and websites
* **Competitive monitoring** — track competitor pricing, product changes, and industry updates

If you have questions or run into any issues, [join the Toolhouse Discord](https://discord.toolhouse.ai/).

***

**Agent Instructions: Querying This Documentation**

If you need additional information not directly available on this page, perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.toolhouse.ai/toolhouse/integrations/tavily-official-partner.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language. The response will contain a direct answer and relevant excerpts from the documentation. Use this when the answer isn't explicitly present on the page, you need clarification, or you want to retrieve related sections.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.toolhouse.ai/toolhouse/integrations/tavily-official-partner.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.