Building Reliable AI Agents with MCP: The Complete Guide

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: "enterprise-metrics-server",
  version: "1.0.0"
});

// Register a type-safe tool with Zod schema validation
server.tool(
  "query_system_metrics",
  { metric: z.enum(["cpu", "memory", "disk"]), durationMinutes: z.number().default(15) },
  async ({ metric, durationMinutes }) => {
    // Isolated execution logic
    const data = { metric, value: 42.5, window: `${durationMinutes}m`, timestamp: new Date().toISOString() };
    return {
      content: [{ type: "text", text: JSON.stringify(data, null, 2) }]
    };
  }
);

async function main() {
  const transport = new StdioServerTransport();
  await server.connect(transport);
  console.error("MCP Server listening on stdio...");
}

main();

from mcp.server.fastmcp import FastMCP
from pydantic import Field

mcp = FastMCP("enterprise-metrics-server")

@mcp.tool()
def query_system_metrics(metric: str = Field(description="cpu, memory, or disk"), duration_minutes: int = 15) -> str:
    # Fetch aggregated system telemetry metrics for cluster nodes
    return f"Metric {metric} average over last {duration_minutes}m: 42.5%"

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