agentsMay 5, 2026· 2 min read

MCP Servers: Giving Agents Real-World Tools

How the Model Context Protocol lets agents use structured tools — databases, APIs, file systems — safely and reliably.

What is MCP?

The Model Context Protocol (MCP) is an open standard for connecting AI models to external tools and data sources. Think of it as a USB-C port for AI — a universal interface that lets any model talk to any tool.

Why MCP Matters

Before MCP, every agent framework had its own tool definition format. If you built a tool for LangChain, you couldn't use it with CrewAI without rewriting it. MCP standardizes this.

The Architecture

Loading diagram...

Building an MCP Server

Here's a minimal MCP server that exposes a database query tool:

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: "database-tools",
  version: "1.0.0",
});

server.tool(
  "query_users",
  "Search for users by name or email",
  {
    search: z.string().describe("Search term"),
    limit: z.number().default(10).describe("Max results"),
  },
  async ({ search, limit }) => {
    const results = await db.query(
      "SELECT id, name, email FROM users WHERE name ILIKE $1 LIMIT $2",
      [`%${search}%`, limit]
    );
    return {
      content: [{ type: "text", text: JSON.stringify(results) }],
    };
  }
);

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