Agent OS

Serve a hotel booking assistant in AgentOS using MCPToolbox hotel and booking toolsets.

agent_os.py

"""
Agent Os
=============================

Demonstrates agent os.
"""

from textwrap import dedent

from agno.agent import Agent
from agno.os import AgentOS
from agno.tools.mcp_toolbox import MCPToolbox

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------


url = "http://127.0.0.1:5001"

mcp_database_tools = MCPToolbox(
    url=url, toolsets=["hotel-management", "booking-system"]
)

agent = Agent(
    tools=[mcp_database_tools],
    instructions=dedent(
        """ \
        You're a helpful hotel assistant. You handle hotel searching, booking and
        cancellations. When the user searches for a hotel, mention it's name, id,
        location and price tier. Always mention hotel ids while performing any
        searches. This is very important for any operations. For any bookings or
        cancellations, please provide the appropriate confirmation. Be sure to
        update checkin or checkout dates if mentioned by the user.
        Don't ask for confirmations from the user.
    """
    ),
    markdown=True,
)


agent_os = AgentOS(
    name="Hotel Assistant",
    description="An agent that helps users find and book hotels.",
    agents=[agent],
)

app = agent_os.get_app()

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    agent_os.serve(app="agent_os:app", reload=True)

Run the Example

1. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   

   uv venv --python 3.12
   .venv\Scripts\activate
   
2. Install dependencies

   uv pip install -U "agno[mcp,os]" openai toolbox-core
   
3. Export your OpenAI API key

   Mac/Linux

   export OPENAI_API_KEY="your_openai_api_key_here"
   

   $Env:OPENAI_API_KEY="your_openai_api_key_here"
   
4. Clone Agno

   Clone the repository and run the remaining commands from its root:

   git clone https://github.com/agno-agi/agno.git
   cd agno
   
5. Start MCP Toolbox

   Start the demo database and toolbox service on port 5001:

   cd cookbook/91_tools/mcp/mcp_toolbox_demo
   docker compose up -d
   cd ../../../..
   
6. Run the example

   Run the example from the repository root:

   python cookbook/91_tools/mcp/mcp_toolbox_demo/agent_os.py
   

Full source: cookbook/91_tools/mcp/mcp_toolbox_demo/agent_os.py