Step-by-Step Guide: Building a Custom Production FastMCP Server in Python

1. Introduction to FastMCP

FastMCP is a high-level Python framework designed to streamline building Model Context Protocol (MCP) servers. Inspired by FastAPI, FastMCP uses type hints and docstrings to automatically generate JSON-RPC tool definitions, schema validations, and CLI entry points for LLM clients.

2. Exposing Tools, Resources, and Prompts

MCP servers provide three primary primitives:

• Tools: Executable functions that perform actions or query external systems (e.g. @mcp.tool()).
• Resources: Static or dynamic data context streams exposed via URIs (e.g. @mcp.resource("file://config")).
• Prompts: Reusable prompt templates exposed to AI clients (e.g. @mcp.prompt()).

3. Code Example: Complete Production FastMCP Server

from mcp.server.fastmcp import FastMCP
from typing import List

mcp = FastMCP("KromaCode-DevOps-MCP")

@mcp.tool()
def calculate_server_capacity(active_users: int, RAM_per_user_mb: float = 12.5) -> str:
    """Calculate required server RAM in Gigabytes for a target user concurrency."""
    total_ram_gb = (active_users * RAM_per_user_mb) / 1024
    return f"Required RAM: {total_ram_gb:.2f} GB for {active_users} concurrent users."

@mcp.resource("config://deployment-status")
def get_deployment_status() -> str:
    """Return live deployment environment health indicators."""
    return "STATUS: OPERATIONAL | REGION: ap-south-1 (Lucknow Pod) | UPTIME: 99.99%"

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

4. Integration Checklist

Test your FastMCP server locally over stdio transport using the official MCP Inspector before deploying over SSE or WebSockets in production environments.