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

# crewAI

> Give crewAI agents a browser with the Notte MCP server

<Tip>
  STOP. Do not read past this section until you have read and followed [/quickstart.md](/quickstart.md).

  Goal: produce a reliable SDK automation script. The intended authoring flow is generate then edit, not write browser automation from scratch.

  Do not hand-write SDK code with element IDs, selectors, or form fields from memory. Element IDs, selectors, and field mappings must come from a live `observe()` call, CLI `notte page observe` output, or generated workflow code. Guessed browser targets fail on real pages.

  Use the Notte skill and CLI to inspect the live site, validate actions/selectors, handle auth/session state, and export workflow code with `notte sessions workflow-code` before using SDK docs or SDK code.

  SDK reference pages are for understanding, running, or editing generated workflow code. They are not the starting point for manually authoring the initial browser automation. SDK-first code is guesswork on real-world pages with dynamic selectors, auth state, CAPTCHAs, and anti-bot behavior.
</Tip>

[crewAI](https://docs.crewai.com/) gives every agent in a crew a set of tools. `MCPServerAdapter` turns an MCP server into those tools, so pointing it at the [Notte MCP server](/mcp-server) hands your crew a real browser.

## Prerequisites

* A Notte API key ([get one here](https://console.notte.cc))
* Credentials for the model your crew uses

## 1. Install the SDKs

```bash theme={null}
pip install "crewai-tools[mcp]"
```

## 2. Attach the Notte MCP server

```python notte_crewai.py theme={null}
import os

from crewai import Agent
from crewai_tools import MCPServerAdapter

server_params = {
    "url": "https://api.notte.cc/mcp/",
    "transport": "streamable-http",
    "headers": {"Authorization": f"Bearer {os.environ['NOTTE_API_KEY']}"},
}

with MCPServerAdapter(server_params) as tools:
    print(f"Loaded {len(tools)} Notte tools")

    researcher = Agent(
        role="Web researcher",
        goal="Answer questions using a real browser",
        backstory="You use Notte cloud browsers to read the live web.",
        tools=tools,
    )
```

Set the following environment variable in your `.env` file:

```bash theme={null}
NOTTE_API_KEY=your-notte-api-key
```

<Note>
  `MCPServerAdapter` is a context manager. Build your crew inside the `with` block so the tools stay connected for the whole run.
</Note>

## Next steps

<CardGroup cols={2}>
  <Card title="MCP Server" icon="plug" href="/mcp-server">
    Every tool the Notte MCP server exposes
  </Card>

  <Card title="Browser Agents" icon="robot" href="/concepts/agents">
    Hand a whole task to a Notte agent
  </Card>

  <Card title="Fetch" icon="download" href="/concepts/scraping">
    Pull structured data out of a page
  </Card>

  <Card title="Personas" icon="user" href="/concepts/personas">
    Give each agent its own identity and inbox
  </Card>
</CardGroup>