Vibe Data Analysis

🚀 Vibe Preprocessing and Analysis MCP Server (for CSV Files)

A powerful MCP (Model Control Protocol) server designed specifically for the preprocessing and analysis of CSV files. This server offers a range of tools to enable data manipulation, visualization, and analysis through an intuitive interface.

✨ Features

Data Loading and Management

• Load CSV files from a specified working directory.
• Set and manage the working directory.
• List files in the working directory.
• Save the processed data frame to a new file.

Data Preprocessing

• Handle columns with mixed data types.
• Manage null values using various strategies:
  • Delete rows containing null values.
  • Fill with mean/median/mode.
  • Forward/backward fill.
  • Fill with a constant.
• Delete and rename columns.
• Execute custom data frame editing code.
• Save the processed data to a new file.

Data Analysis

• Generate comprehensive data descriptions.
• Create and visualize correlation matrices.
• Handle columns with mixed data types.
• Execute custom analysis code.

Data Visualization

• Create various types of charts:
  • Line charts
  • Bar charts
  • Scatter plots
  • Histograms (with KDE)
  • Box plots
  • Violin plots
  • Pie charts
  • Count plots
  • Kernel density estimation plots
• Generate custom charts via code.
• Save visualization results to the working directory.
• Execute custom visualization code.

📦 Installation

Prerequisites

• Python 3.x
• uv (recommended package manager). It is recommended to use uv to manage the server.

Installation Steps

1. Add MCP and its dependencies:

uv add "mcp[cli]"
uv add pandas matplotlib seaborn numpy

2. Install the server in Claude Desktop:

mcp install server.py

Alternative Installation with pip

If you prefer to use pip:

pip install "mcp[cli]" pandas matplotlib seaborn numpy

💻 Usage Examples

Basic Usage

1. Start the MCP server:

uv run mcp

2. Test the server using the MCP checker:

mcp dev server.py

You can install this server in Claude Desktop and immediately interact with it by running the following command:

mcp install server.py

Alternatively, you can test it using the MCP checker:

mcp dev server.py

📚 Documentation

Available Tools

Data Management

• send_work_dir(): Get the current working directory.
• set_work_dir(new_work_dir): Set a new working directory.
• list_work_dir_files(): List files in the working directory.
• load_csv(filename): Load a CSV file into the system.
• save_global_df(filename): Save the current data frame to a file.

Data Preprocessing

• handle_column_mixed_types(): Handle columns with mixed data types.
• handle_null_values(strategy, columns): Manage null values using various strategies.
• drop_columns(columns): Delete specified columns.
• rename_columns(column_mapping): Rename columns in the data frame.
• run_custom_df_edit_code(code): Execute custom data frame editing code.

Data Analysis

• describe_df(): Generate a statistical summary of the data frame.
• generate_correlation_matrix(): Create and visualize a correlation matrix.

Data Visualization

• plot_graph(graph_type, x_column, y_column, output_filename): Create various types of charts. Supported chart types: 'line', 'bar', 'scatter', 'histogram', 'box', 'violin', 'pie', 'count'.
• run_custom_viz_code(code): Execute custom visualization code.

Environment Variables

• WORK_DIR: The default working directory path for the server.

Error Handling

• Supports various error types, including file not found, invalid parameters, etc.