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

# Airbnb Agent

> Serve an Airbnb search agent built on the OpenBNB MCP server over the A2A protocol.

```python airbnb_agent.py theme={null}
"""
Airbnb Agent
============

Demonstrates airbnb agent.
"""

from textwrap import dedent

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.os import AgentOS
from agno.tools.mcp import MCPTools

# ---------------------------------------------------------------------------
# Create Example
# ---------------------------------------------------------------------------

airbnb_agent = Agent(
    id="airbnb-search-agent",
    name="Airbnb Search Agent",
    description="A specialized agent for finding and detailing Airbnb listings using the OpenBNB MCP server.",
    model=OpenAIChat(id="gpt-4o"),
    tools=[MCPTools("npx -y @openbnb/mcp-server-airbnb --ignore-robots-txt")],
    instructions=dedent("""
        You are an expert travel assistant.
        Use the 'airbnb_search' tool to find properties based on location, dates, and people.
        For detailed listing information, use 'airbnb_listing_details'.
        Always provide location, price, and a link in your final response.
    """),
    markdown=False,
)

agent_os = AgentOS(
    id="airbnb-agent-os",
    description="An AgentOS serving specialized Agent for Airbnb search",
    agents=[
        airbnb_agent,
    ],
    a2a_interface=True,
)
app = agent_os.get_app()


# ---------------------------------------------------------------------------
# Run Example
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    """Run your AgentOS.
    You can run the Agent via A2A protocol:
    POST http://localhost:7774/agents/{id}/v1/message:send
    For streaming responses:
    POST http://localhost:7774/agents/{id}/v1/message:stream
    Retrieve the agent card at:
    GET  http://localhost:7774/agents/{id}/.well-known/agent-card.json
    """
    agent_os.serve(app="airbnb_agent:app", port=7774, reload=True)
```

## Run the Example

<Steps>
  <Snippet file="create-venv-step.mdx" />

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U "agno[a2a,mcp,os]" openai
    ```
  </Step>

  <Step title="Prepare Node.js">
    The MCP server runs with `npx`. Install Node.js, then verify the commands:

    ```bash theme={null}
    node --version
    npx --version
    ```
  </Step>

  <Step title="Export your OpenAI API key">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
      export OPENAI_API_KEY="your_openai_api_key_here"
      ```

      ```bash Windows theme={null}
      $Env:OPENAI_API_KEY="your_openai_api_key_here"
      ```
    </CodeGroup>
  </Step>

  <Step title="Run the example">
    Save the code above as `airbnb_agent.py`, then run:

    ```bash theme={null}
    python airbnb_agent.py
    ```
  </Step>
</Steps>

Full source: [cookbook/05\_agent\_os/15\_a2a/multi\_agent/airbnb\_agent.py](https://github.com/agno-agi/agno/blob/main/cookbook/05_agent_os/15_a2a/multi_agent/airbnb_agent.py)