From 1, The one-liner for MCP as follows

The Model Context Protocol is an open standard that enables developers to build secure, two-way connections between their data sources and AI-powered tools.

MCP sounds like a good approach for extendible agentic tools

First example Link to heading

Step 1, First install mcp

pip install mcp

Step 2, The server with a tool and resource

# server.py
from mcp.server.fastmcp import FastMCP

# Create an MCP server
mcp = FastMCP("Demo")

# Add an addition tool
@mcp.tool()
def add(a: int, b: int) -> int:
    """Add two numbers"""
    return a + b

# Add a dynamic greeting resource
@mcp.resource("greeting://{name}")
def get_greeting(name: str) -> str:
    """Get a personalized greeting"""
    return f"Hello, {name}!"

Step 3, Run the dev server

mcp dev server.py

Step 4, One way to call tools and resource is using the web interface

Opening http://localhost:5173 in the browser gives us access to the tools and resources defined