About Create a Custom Server
A Python tutorial project for developers building an MCP calculator server for AI assistants. It demonstrates four basic arithmetic tools and connection setup with Claude for Desktop.
Key features
- 01Addition, subtraction, multiplication, and division
- 02Build a server with the Python MCP SDK
- 03Run over stdio transport
- 04Configure Claude for Desktop
Use cases
- 01Perform basic arithmetic in conversations
- 02Learn to build a custom MCP server
MCP support
The example MCP server exposes add, subtract, multiply, and divide tools to clients. The tutorial shows how to run it over stdio and configure Claude for Desktop to connect.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMECreate a Custom Server
Get started building your own server to use in Claude for Desktop and other clients.
In this tutorial, we'll build a simple MCP calculator server and connect it to a host, Claude for Desktop.
What is MCP?
MCP stands for Model Context Protocol — it’s a protocol that allows developers to extend AI assistants (like Claude) with custom tools and servers.
- Think of it like giving your AI assistant extra powers.
- These servers expose tools or functionalities that the assistant can use during a conversation.
- For example: you can build weather servers, calculators, finance assistants, or anything you imagine.
What We'll Be Building
We'll build a server that exposes four tools: add, subtract, multiply, and divide. Then we'll connect the server to an MCP host (in this case, Claude for Desktop):
Note: Servers can connect to any client. We've chosen Claude for Desktop here for demonstration purposes.
Why Claude for Desktop and not Claude.ai?
Because servers are locally run, MCP currently only supports desktop hosts.Core MCP Concepts
MCP servers can provide three main types of capabilities:
- Resources: File-like data that can be read by clients (like API responses or file contents).
- Tools: Functions that can be called by the LLM (with user approval).
- Prompts: Pre-written templates that help users accomplish specific tasks.
This tutorial will primarily focus on tools.
Let's get started with building our calculator server! You can find the complete code for what we'll be building here.
Prerequisite Knowledge
This quickstart assumes you have familiarity with:
- Python
- LLMs like Claude
System Requirements
- Python 3.10 or higher installed.
- You must use the Python MCP SDK 1.2.0 or higher.
Set Up Your Environment
First, let's install uv and set up our Python project and environment:
MacOS/Linux
curl -LsSf https://astral.sh/uv/install.sh | sh
Windows
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
Make sure to restart your terminal afterwards to ensure that the uv command gets picked up.
Now, let's create and set up our project:
MacOS/Linux
# Create a new directory for our project
uv init calculator
cd calculator
# Create virtual environment and activate it
uv venv
source .venv/bin/activate
# Install dependencies
uv add "mcp[cli]"
# Create our server file
touch calculator.py
Windows
# Create a new directory for our project
uv init calculator
cd calculator
# Create virtual environment and activate it
uv venv
.venv\Scripts\activate
# Install dependencies
uv add "mcp[cli]"
# Create our server file
new-item calculator.py
Now let's dive into building your server.
Building Your Server
Importing Packages and Setting Up the Instance
Add these to the top of your calculator.py:
from mcp.server.fastmcp import FastMCP
# Initialize FastMCP server
mcp = FastMCP("calculator")
Implementing Tool Execution
The tool execution handler is responsible for actually executing the logic of each tool. Let's add it:
@mcp.tool()
def add(a: float, b: float) -> float:
"""Add two numbers."""
return a + b
@mcp.tool()
def subtract(a: float, b: float) -> float:
"""Subtract two numbers."""
return a - b
@mcp.tool()
def multiply(a: float, b: float) -> float:
"""Multiply two numbers."""
return a * b
@mcp.tool()
def divide(a: float, b: float) -> float:
"""Divide two numbers."""
if b == 0:
raise ValueError("Division by zero is not allowed.")
return a / b
Running the Server
Finally, let's initialize and run the server:
if __name__ == "__main__":
# Initialize and run the server
mcp.run(transport='stdio')
Your server is complete! Run uv run calculator.py to confirm that everything's working.
Testing Your Server with Claude for Desktop
Note: Claude for Desktop is not yet available on Linux.
We'll need to configure Claude for Desktop for whichever MCP servers you want to use. To do this, open your Claude for Desktop App configuration at ~/Library/Application Support/Claude/claude_desktop_config.json in a text editor. Make sure to create the file if it doesn't exist.
MacOS/Linux
code ~/Library/Application\ Support/Claude/claude_desktop_config.json
Windows
code $env:AppData\Claude\claude_desktop_config.json
You'll then add your servers in the mcpServers key. The MCP UI elements will only show up in Claude for Desktop if at least one server is properly configured.
In this case, we'll add our single calculator server like so:
MacOS/Linux
{
"mcpServers": {
"calculator": {
"command": "uv",
"args": [
"--directory",
"/ABSOLUTE/PATH/TO/PARENT/FOLDER/calculator",
"run",
"calculator.py"
]
}
}
}
Windows
{
"mcpServers": {
"calculator": {
"command": "uv",
"args": [
"--directory",
"C:\\ABSOLUTE\\PATH\\TO\\PARENT\\FOLDER\\calculator",
"run",
"calculator.py"
]
}
}
}
Warning: You may need to put the full path to the
uvexecutable in thecommandfield. You can get this by runningwhich uvon MacOS/Linux orwhere uvon Windows.
Make sure you pass in the absolute path to your server.
This tells Claude for Desktop:
- There's an MCP server named "calculator".
- To launch it by running
uv --directory /ABSOLUTE/PATH/TO/PARENT/FOLDER/calculator run calculator.py.
Save the file, and restart Claude for Desktop.
Since this calculator supports basic arithmetic operations, it can be used for addition, subtraction, multiplication, and division.
For more info: MCP Official Docs
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.