Example AgentOS app with MCP enabled

Enable an LLM-friendly MCP server at /mcp on an AgentOS serving a web research agent via mcp_server=True.

After starting this AgentOS app, you can test the MCP server with the test_client.py file.

mcp_server_example.py

"""
Example AgentOS app with MCP enabled.

After starting this AgentOS app, you can test the MCP server with the test_client.py file.
"""

from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.models.anthropic import Claude
from agno.os import AgentOS
from agno.tools.websearch import WebSearchTools

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

# Setup the database
db = SqliteDb(db_file="tmp/agentos.db")

# Setup basic research agent
web_research_agent = Agent(
    id="web-research-agent",
    name="Web Research Agent",
    model=Claude(id="claude-sonnet-4-5"),
    db=db,
    tools=[WebSearchTools()],
    add_history_to_context=True,
    num_history_runs=3,
    add_datetime_to_context=True,
    enable_session_summaries=True,
    markdown=True,
)


# Setup our AgentOS with MCP enabled
agent_os = AgentOS(
    description="Example app with MCP enabled",
    agents=[web_research_agent],
    mcp_server=True,  # This enables a LLM-friendly MCP server at /mcp
)

app = agent_os.get_app()

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

if __name__ == "__main__":
    """Run your AgentOS.

    You can see view your LLM-friendly MCP server at:
    http://localhost:7777/mcp

    """
    agent_os.serve(app="mcp_server_example:app")

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]" anthropic ddgs
   
3. Export your Anthropic API key

   Mac/Linux

   export ANTHROPIC_API_KEY="your_anthropic_api_key_here"
   

   $Env:ANTHROPIC_API_KEY="your_anthropic_api_key_here"
   
4. Run the example

   Save the code above as mcp_server_example.py, then run:

   python mcp_server_example.py
   

Full source: cookbook/05_agent_os/mcp_demo/mcp_server_example.py