Model Context Protocol (MCP)

What is MCP?

Model Context Protocol is an open standard that lets AI models (like Claude) connect to external tools, databases, and APIs through a unified interface.

Think of it as a USB standard for AI — any MCP-compatible client can talk to any MCP server.

Architecture

Claude (MCP Client)
    ↕ MCP Protocol
MCP Server
    ↕
Your Tools / APIs / Databases

MCP Server Capabilities

Type	Description	Example
Tools	Functions the AI can call	Run SQL query, send email
Resources	Data the AI can read	File contents, DB records
Prompts	Reusable prompt templates	Summarize document

Building a Simple MCP Server (Python)

from mcp.server import Server
from mcp.server.stdio import stdio_server
from mcp import types

app = Server("my-server")

@app.list_tools()
async def list_tools():
    return [
        types.Tool(
            name="get_weather",
            description="Get current weather for a city",
            inputSchema={
                "type": "object",
                "properties": {
                    "city": {"type": "string"}
                },
                "required": ["city"]
            }
        )
    ]

@app.call_tool()
async def call_tool(name: str, arguments: dict):
    if name == "get_weather":
        city = arguments["city"]
        # call your weather API here
        return [types.TextContent(type="text", text=f"Sunny in {city}, 28°C")]

async def main():
    async with stdio_server() as (read, write):
        await app.run(read, write, app.create_initialization_options())

Configuring MCP in Claude Code

Add to ~/.claude/settings.json:

{
  "mcpServers": {
    "my-server": {
      "command": "python",
      "args": ["/path/to/server.py"]
    }
  }
}

Common MCP Servers

• filesystem — read/write local files
• postgres — query PostgreSQL databases
• github — interact with GitHub repos
• fetch — fetch web pages
• sqlite — query SQLite databases