MCP Python Tutorial

Tutorial app for MCP in Python with simple local DB with mocking data

Installation & Run

Installing via Smithery

To install Python MCP Tutorial Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @jhj0517/mcp-python-tutorial --client claude

Manual Installation

Clone this repository
Install dependencies:

pip install -r requirements.txt

Run MCP server as dev mode:

mcp dev localdb_app.py

Default port for MCP server is 5173. Access to http://localhost:5173.

MCP Features

This tutorial app demonstrates core MCP concepts. You can check annotation-per-role in tutorial_app/mcp_server.py:

`@mcp.resource`

Basically, this annotation is about the agent "getting" the resource, just like GET in the RESTAPI.

users://all - Get all users
users://{user_id}/profile - Get a user's profile
posts://all - Get all posts
posts://{post_id} - Get a post by ID

`@mcp.tool`

This is about the agent "generating" the new resource, just like POST in the RESTAPI.

create_user - Create a new user
create_post - Create a new post
search_posts - Search posts by title or content

`@mcp.prompt`

This is just a reusable template to interact with LLM conveniently.

user_profile_analysis - Generate analysis of a user's profile
post_feedback - Interactive prompt for post feedback

Note

For more annotations, please read : https://github.com/modelcontextprotocol/python-sdk?tab=readme-ov-file#core-concepts

Connecting to Client

Once you've set up the MCP server, you need an LLM client that will use your MCP server to build your agent. The following guide will help you connect with Claude Desktop as your client.

Claude Desktop uses uv to install MCP server dependencies. First, install uv:

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Install MCP server dependencies using uv:

# Create virtual environment and activate it
uv venv
.venv\Scripts\activate

uv pip install -r requirements.txt

Download Claude Desktop from:

https://claude.ai/download

Locate or create the claude_desktop_config.json file. The location varies by OS:

Windows:

C:\Users\%USER%\AppData\Roaming\Claude\claude_desktop_config.json

MacOS/Linux:

~/Library/Application\ Support/Claude/claude_desktop_config.json

Add the mcpServers attribute to your claude_desktop_config.json:

{
    "mcpServers": {
        "local_db": {
            "command": "uv",
            "args": [
                "--directory",
                "/ABSOLUTE/PATH/TO/PARENT/FOLDER/weather",
                "run",
                "localdb_app.py"
            ]
        }
    }
}

Note: You can deploy multiple MCP servers, each with its own dedicated concerns and expertise. This separation of concerns is better than implementing everything in a single MCP server.

Restart Claude Desktop.

MCP Python Tutorial

Integrations