Titanicaianalysis

🚀 Project Documentation: Analyzing the Titanic Dataset with Claude AI and MCP Protocol

This project demonstrates how to leverage Claude AI and the MCP protocol to analyze the Titanic passenger dataset. The documentation details all aspects of the project, including installation, configuration, and usage of relevant tools.

🚀 Quick Start

This project aims to integrate the Titanic dataset into Claude via MCP (Model Context Protocol), enabling it to dynamically answer complex questions about the data. We provide preprocessed data and specific features to assist users in in - depth analysis.

✨ Features

• Data Update: The server loads the latest data for each query.
• Structured Data: Claude can directly process preprocessed data.
• Dynamic Analysis: Supports custom questions regarding the data.

📦 Installation

Step 1: Clone the project repository

Use Git to clone this repository to your local machine:

git clone https://github.com/yourusername/titanic-mcp.git

Step 2: Install dependencies

Navigate to the project directory and install the required Python packages:

pip install -r requirements.txt

Step 3: Start the MCP server

Run the following command to start the MCP server:

python server.py

💻 Usage Examples

Connect to Claude Desktop

1. Open Claude Desktop.
2. In the settings menu, select the "Developer" option, then edit the configuration file (claude_desktop_config.json).
3. Add the following content to configure the MCP server:

   {
     "mcpServers": {
       "TitanicServerMCP": {
         "command": "python",
         "args": ["path/to/titanic-mcp/server.py"]
       }
     }
   }
   

4. Save the configuration file and restart Claude Desktop.

Use resources and tools

• Resources:
  • titanic://passengers: The complete Titanic passenger dataset.
  • titanic://statistics: Pre - computed survival rate statistics.
• Tools:
  • search_passenger: Search for information about specific passengers by name.

Typical queries

Here are some typical queries you can make using Claude:

1. "Show the survival statistics of passengers on the Titanic."
2. "Compare the survival rate percentages of first - class and third - class passengers."
3. "Find information about passengers with the last name 'Astor'."
4. "Analyze the correlation between social class and survival rate."

📚 Documentation

System Requirements

• Python: You need to install the latest version of Python to run the MCP server.
• Claude Desktop: Ensure you have installed a compatible version of the Claude desktop application.
• Data File: Provide the Titanic passenger dataset (in CSV format).

Advantages and Disadvantages

Advantages

• The server loads the latest data for each query.
• Claude can directly process preprocessed data.
• It supports custom questions regarding the data.

Disadvantages

• Data Volume Limitation: Large datasets may exceed the size of Claude's context window.
• Resource Update Frequency: Resources are only loaded upon request.

Possible Extensions

1. Parameterized Resources: For example, titanic://passengers/{class}.
2. Advanced Analysis Tools: Add complex statistical calculation functions.
3. Visualization Support: Integrate functions to generate charts and graphs.
4. Database Connection: Expand the data source from CSV files to databases.
5. Prediction Model: Pre - load machine learning models to provide survival probability predictions.

Thank you for using this project! For more information, please visit our GitHub repository or contact the maintainers.