Canpolat Kaya

AI Architecture

Model Context Protocol (MCP) Guide: Connecting LLMs to Local Databases and Tools

Learn the open-source Model Context Protocol (MCP) standard created by Anthropic and how it turns LLMs into extensible agents connected to your infrastructure.

3 min

Summary & Direct Solution (TL;DR)

Model Context Protocol (MCP) is an open-source standard created by Anthropic that allows large language models (LLMs) to securely access local databases, internal APIs, file systems, and development tools. It functions like a universal 'USB-C port for AI', eliminating bespoke integrations with a standardized JSON-RPC server architecture.

Key Technical Takeaways:

  • Universal Integration Protocol: Standardizes communication between LLMs and PostgreSQL, GitHub, Slack, or local tools.
  • Strict Isolation & Security: Enforces granular permission boundaries on which tools and local resources models can invoke.
  • Widespread Ecosystem Adoption: Supported natively in Claude Desktop, Cursor, Claude Code, and open-source agent runtimes.

Why Was the MCP Standard Created?

Previously, every AI tool (Cursor, Claude Desktop, local agents) required proprietary plugin architectures to connect to databases, file systems, or GitHub.

Model Context Protocol (MCP) establishes a universal standard—similar to USB-C for AI—eliminating custom integration overhead between LLMs and data sources.

Building a Simple MCP Server with TypeScript

Exposing a local PostgreSQL database to Claude and MCP-compliant tools with a structured server:

mcp-server.ts
import { Server } from "@modelcontextprotocol/sdk/server/index.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import { ListToolsRequestSchema } from "@modelcontextprotocol/sdk/types.js";

const server = new Server({ name: "db-mcp-server", version: "1.0.0" }, { capabilities: { tools: {} } });

server.setRequestHandler(ListToolsRequestSchema, async () => ({
  tools: [{
    name: "run_sql_query",
    description: "Executes read-only SQL queries on the database",
    inputSchema: {
      type: "object",
      properties: { query: { type: "string", description: "SQL SELECT query to execute" } },
      required: ["query"]
    }
  }]
}));

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

Frequently Asked Questions

Which IDEs and platforms support MCP?

Claude Desktop, Cursor, Zed, Windsurf, and Claude Code all provide native support for MCP servers.

Verified Documentation & Sources