Get the FREE Ultimate OpenClaw Setup Guide →

mcp -templates

This repository provides a template for setting up Model Context Protocol (MCP) servers for local development.

Installation
Run this command in your terminal to add the MCP server to Claude Code.
Run in terminal:
Command
claude mcp add --transport stdio gupta-ujjwal-mcp-server-templates python servers/notes.py

How to use

This MCP server bundle provides three example servers you can run locally: Weather, Calculator, and Notes. Each server exposes MCP-compatible endpoints and tooling through the Python implementations located under the servers directory. Use the MCP dev command to start a specific server (for example, mcp dev servers/weather.py) or configure VS Code integration to launch the servers via your workspace settings. The Weather server offers weather alerts and forecasts, the Calculator server provides basic and advanced mathematical operations, and the Notes server enables simple note-taking with local storage. Once running, you can query each service using the MCP protocol, obtain responses, and integrate them with AI assistants or other MCP-enabled tools.

How to install

Prerequisites:

  • Python 3.10+
  • Git
  • Internet access to install dependencies
  • (Optional) UV package manager for faster installations

Step-by-step installation:

  1. Clone the repository git clone <repository-url> cd mcp-server-templates

  2. (Recommended) Create and activate a virtual environment python -m venv venv

    macOS/Linux

    source venv/bin/activate

    Windows

    venv\Scripts\activate.bat

  3. Install UV (recommended for faster installs) if you plan to use it pip install uv

  4. Install Python dependencies uv pip install -r requirements.txt

  5. Run an MCP server

    • Weather: mcp dev servers/weather.py
    • Calculator: mcp dev servers/calculator.py
    • Notes: mcp dev servers/notes.py
  6. Optional: Set up VS Code integration by adding the provided mcp settings to your settings.json (as shown in the README) to easily start each server from the editor.

Additional notes

Tips and common issues:

  • Ensure you are using Python 3.10+ per the project requirements.
  • Activate your virtual environment before installing dependencies.
  • If you encounter module import errors, double-check that your working directory is the repository root when running mcp dev commands.
  • The example servers are intended for local development; you can extend them or replace with your own MCP servers by following the same file structure.
  • When using UV, you can replace pip/venv commands with uv pip install -r requirements.txt to streamline setup.
  • If you see port or path conflicts, verify that the script paths (servers/weather.py, servers/calculator.py, servers/notes.py) exist and are accessible from the current directory.
  • Refer to the MCP documentation linked in the repository for protocol specifics and integration guidance.

Related MCP Servers

Sponsor this space

Reach thousands of developers