mcp-builder

MCP Builder

What is MCP

Model Context Protocol is the open standard for connecting AI agents to external tools and data sources. Think of it as USB-C for AI — one standard connector to any tool.

When to use MCP: When you want a tool to be reusable across multiple agents or platforms (Claude, Copilot, Cursor, etc.)

When NOT to use MCP: For project-specific, one-off integrations where the overhead isn't worth it.

---

MCP Server Structure

my-mcp-server/
├── server.py (Python) or index.ts (TypeScript)
├── tools/
│   ├── tool_one.py
│   └── tool_two.py
├── resources/       # Optional: expose data sources
├── prompts/         # Optional: expose prompt templates
├── requirements.txt or package.json
└── README.md

---

Python (FastMCP) — Recommended

from fastmcp import FastMCP

mcp = FastMCP("my-server-name")

@mcp.tool()
def get_user(user_id: str) -> dict:
    """
    Retrieve a user by their ID.
    
    Args:
        user_id: The unique identifier of the user
    
    Returns:
        User object with id, name, email
    """
    # implementation
    return {"id": user_id, "name": "James", "email": "[email protected]"}

@mcp.tool()
def create_task(title: str, description: str, assignee: str = None) -> dict:
    """Create a new task in the project management system."""
    # implementation
    return {"id": "task_123", "title": title, "status": "created"}

if __name__ == "__main__":
    mcp.run()

---

TypeScript (MCP SDK)

import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js"
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js"
import { z } from "zod"

const server = new McpServer({ name: "my-server", version: "1.0.0" })

server.tool(
  "get_user",
  "Retrieve a user by their ID",
  { userId: z.string().describe("The user's unique ID") },
  async ({ userId }) => ({
    content: [{ type: "text", text: JSON.stringify({ id: userId, name: "James" }) }]
  })
)

const transport = new StdioServerTransport()
await server.connect(transport)