Vault Python MCP Server

🚀 MCP Calculator Server

An implementation of the Model Context Protocol (MCP) server with a basic calculator tool. This server can be deployed on Smithery and provides arithmetic operations through a REST API.

🚀 Quick Start

The MCP Calculator Server is a powerful tool that allows you to perform arithmetic operations via a REST API. Here's how you can get started:

📦 Installation

Create a virtual environment and install dependencies

1. Create and activate a virtual environment in the project directory:

   python -m venv env
   source env/bin/activate  # For Unix/Mac
   # Or
   .\env\Scripts\activate  # For Windows
   

2. Install the dependencies:

   pip install -r requirements.txt
   

💻 Usage Examples

Start the server (HTTP mode)

uvicorn server:app --host 0.0.0.0 --port 8000

Start the server (WebSocket mode)

python -m server.websocket_server

Start the server (Standard input/output mode)

python -m server.stdin_stdout_server

✨ Features

• Basic Arithmetic Operations: Supports addition, subtraction, multiplication, and division.
• MCP-Compatible API Endpoints: Ensures seamless integration with MCP systems.
• JSON Schema Validation: Validates input data to ensure accuracy.
• Error Handling: Automatically captures and logs errors, and supports custom error handling logic.
• Multiple Communication Methods: Supports HTTP, WebSocket, and standard input/output.
• Integration Support: Supports integration with both local and remote tools.

📚 Documentation

API Endpoints

HTTP Mode Endpoints

• GET /: Returns server status information.
• POST /add: Accepts two numbers and returns their sum.
• POST /subtract: Accepts two numbers and returns the result of the first number minus the second number.
• POST /multiply: Accepts two numbers and returns their product.
• POST /divide: Accepts two numbers and returns the result of the first number divided by the second number.

WebSocket Mode Endpoint

• ws://localhost:8001/ws: Supports real-time interactive calculations.

Deployment Instructions

Containerized Deployment (Docker)

Create a Docker image (HTTP mode)

# Use the official Python base image
FROM python:3.9-slim

# Set the working directory
WORKDIR /app

# Copy dependencies and source files
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy the server code
COPY server .

# Expose port 8000
EXPOSE 8000

# Set the startup command
CMD ["uvicorn", "server:app", "--host", "0.0.0.0", "--port", "8000"]

Create a Docker image (Standard input/output mode)

# Use the official Python base image
FROM python:3.9-slim

# Set the working directory
WORKDIR /app

# Copy dependencies and source files
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy the server code
COPY server .

# Expose standard input/output
EXPOSE 1

# Set the startup command
CMD ["python", "-m", "server.stdin_stdout_server"]

Integration Configuration

Smithery Configuration (Local Tool)

{
  "name": "calculator",
  "description": "A basic calculator capable of performing arithmetic operations",
  "command": ["python", "server.py"],
  "env": {
    "MCP_STDIO_MODE": "1",
    "LOGGING_CONFIG": "stdio"
  },
  "type": "local"
}

Smithery Configuration (Remote Tool)

{
  "name": "calculator",
  "description": "A basic calculator capable of performing arithmetic operations",
  "url": "http://your-container-host:8000/mcp",
  "type": "remote"
}

🔧 Technical Details

• Error Handling: The server automatically captures and logs error information and supports custom error handling logic.

📄 Notes

⚠️ Important Note

For local tool integration, ensure that you use the standard input/output mode (MCP_STDIO_MODE=1) and configure the LOGGING_CONFIG environment variable.

💡 Usage Tip

When running in a container environment, it is recommended to use the uvicorn startup command directly for more reliable signal handling and startup processes.

With the above documentation, you can easily deploy and integrate the MCP Calculator Server into various projects.