mcp-server-development

MCP Server Development

Build Model Context Protocol servers that expose tools, resources, and prompts to AI coding agents.

When to Use

• Building a tool server for Copilot, Claude, or other MCP-compatible agents
• Exposing an API, database, or service as agent-callable tools
• Creating reusable prompt templates for agent workflows
• Providing file/resource access to agents through a standard protocol

Decision Tree

Need to expose capabilities to AI agents?
+- Read-only data access?
| - Use MCP Resources (URI-based, typed)
+- Execute actions / side effects?
| - Use MCP Tools (JSON Schema input, structured output)
+- Reusable prompt templates?
| - Use MCP Prompts (parameterized, multi-turn)
- Combine multiple?
 - Single MCP server with mixed capabilities

Architecture Overview

-------------- stdio/SSE --------------
| AI Agent | ------------- | MCP Server |
| (Copilot) | JSON-RPC 2.0 | (your code) |
-------------- ------+-------
 |
 -------------+-------------
 | | |
 Tools Resources Prompts
 (actions) (read data) (templates)

Quick Start: TypeScript

npm init -y
npm install @modelcontextprotocol/sdk zod

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",
});

// Tool: execute actions
server.tool("greet", { name: z.string() }, async ({ name }) => ({
 content: [{ type: "text", text: `Hello, ${name}!` }],
}));

// Resource: read-only data
server.resource("config", "config://app", async () => ({
 contents: [{ uri: "config://app", text: JSON.stringify({ env: "prod" }) }],
}));

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

Quick Start: Python

pip install mcp

from mcp.server.fastmcp import FastMCP

mcp = FastMCP("my-server")

@mcp.tool()
def greet(name: str) -> str:
 """Greet a user by name."""
 return f"Hello, {name}!"

@mcp.resource("config://app")
def get_config() -> str:
 """Read application configuration."""
 return '{"env": "prod"}'

# Run: python server.py