> ## 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.

# Agno

> Give Agno 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>

[Agno](https://docs.agno.com/) ships an `MCPTools` toolkit that connects an agent to any MCP server. Point it at the [Notte MCP server](/mcp-server) to give your agent sessions, browser agents, scraping and functions.

## Prerequisites

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

## 1. Install the SDKs

```bash theme={null}
pip install agno mcp
```

## 2. Attach the Notte MCP server

```python notte_agno.py theme={null}
import asyncio
import os

from agno.agent import Agent
from agno.models.anthropic import Claude
from agno.tools.mcp import MCPTools


async def main():
    # Notte authenticates with a bearer token, so use header_provider
    async with MCPTools(
        url="https://api.notte.cc/mcp/",
        transport="streamable-http",
        header_provider=lambda: {"Authorization": f"Bearer {os.environ['NOTTE_API_KEY']}"},
    ) as notte_tools:
        print(f"Loaded {len(notte_tools.functions)} Notte tools")

        agent = Agent(model=Claude(id="claude-sonnet-4-5-20250929"), tools=[notte_tools])
        await agent.aprint_response("What is the H1 on https://example.com?")


asyncio.run(main())
```

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

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

<Note>
  Pass the bearer token through `header_provider`, not `headers` - `MCPTools` forwards `header_provider` to the HTTP transport and rejects a bare `headers` argument.
</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="Functions" icon="https://mintcdn.com/notte/laVxhSjtZz3-wqG3/logo/square-function.svg?fit=max&auto=format&n=laVxhSjtZz3-wqG3&q=85&s=d294a42f7a09939e5a532b4b524541f4" href="/concepts/functions" width="24" height="24" data-path="logo/square-function.svg">
    Turn a working run into a callable function
  </Card>
</CardGroup>