MCP Graphiti Agent - A personal diary assistant

Use Agno’s MCP integration together with Graphiti, to build a personal diary assistant.

Use Agno’s MCP integration with Graphiti to build a personal diary assistant that stores and recalls entries from a knowledge graph.

graphiti.py

"""
 MCP Graphiti Agent - A personal diary assistant

This example demonstrates how to use Agno's MCP integration together with Graphiti, to build a personal diary assistant.

- Run your Graphiti MCP server. Full instructions: https://github.com/getzep/graphiti/tree/main/mcp_server
- Run: `uv pip install agno mcp openai` to install the dependencies
"""

import asyncio
from textwrap import dedent

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

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


mcp_server_url = "http://localhost:8000/sse"


async def run_agent(message: str) -> None:
    async with MCPTools(url=mcp_server_url, transport="sse") as mcp_tools:
        agent = Agent(
            tools=[mcp_tools],
            model=OpenAIChat(id="o3-mini"),
            instructions=dedent(
                """
                You are an assistant with access to tools related to Graphiti's knowledge graph capabilities.
                You maintain a diary for the user.
                Your job is to help them add new entries and use the diary data to answer their questions.
                """
            ),
        )
        await agent.aprint_response(message, stream=True)


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

if __name__ == "__main__":
    asyncio.run(
        # Using the agent to add new entries to the diary
        run_agent(
            "Add the following entry to the diary: 'Today I spent some time building agents with Agno'"
        )
    )

    asyncio.run(
        # Using the agent to answer questions about the diary
        run_agent("What have I been building recently?")
    )

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]" openai
   
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. Start Graphiti MCP

   Start a Graphiti MCP server at http://localhost:8000/sse. See the Graphiti MCP server instructions.

5. Run the example

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

   python graphiti.py
   

Full source: cookbook/91_tools/mcp/graphiti.py