Linear Regression MCP

By HeetVekariya GitHub

MCP server for training Linear Regression Model.

mcp linear-regression

Overview

What is Linear Regression MCP?

Linear Regression MCP is a project that demonstrates an end-to-end machine learning workflow using Claude and the Model Context Protocol (MCP) to train a Linear Regression model.

How to use Linear Regression MCP?

To use this project, clone the repository, install the necessary dependencies, and configure Claude Desktop to link with the MCP server. You can then upload a CSV file containing your dataset to train the model.

Key features of Linear Regression MCP?

End-to-end machine learning model training lifecycle.
Automatic data preprocessing, training, and evaluation (RMSE calculation).
Tools for uploading datasets and checking column information.

Use cases of Linear Regression MCP?

Training linear regression models for predictive analytics.
Evaluating model performance using RMSE.
Preprocessing datasets for machine learning tasks.

FAQ from Linear Regression MCP?

Can I use any dataset?

Yes, as long as it is in CSV format and contains the necessary columns for training.

Is there a specific Python version required?

The project is compatible with Python 3.x.

How can I contribute to this project?

You can fork the repository, make changes, and submit a pull request.

Content

Linear Regression MCP

Welcome to Linear Regression MCP! This project demonstrates an end-to-end machine learning workflow using Claude and the Model Context Protocol (MCP).

Claude can train a Linear Regression model entirely by itself, simply by uploading a CSV file containing the dataset. The system goes through the entire ML model training lifecycle, handling data preprocessing, training, and evaluation (RMSE calculation).

Setup and Installation

1. Clone the Repository:

First, clone the repository to your local machine:

git clone https://github.com/HeetVekariya/Linear-Regression-MCP
cd Linear-Regression-MCP

2. Install `uv`:

uv is an extremely fast Python package and project manager, written in Rust. It is essential for managing the server and dependencies in this project.

Download and install uv from here.

3. Install Dependencies:

Once uv is installed, run the following command to install all necessary dependencies:

uv sync

4. Configure Claude Desktop:

To integrate the server with Claude Desktop, you will need to modify the Claude configuration file. Follow the instructions for your operating system:

For macOS or Linux:

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

For Windows:

code $env:AppData\Claude\claude_desktop_config.json

In the configuration file, locate the mcpServers section, and replace the placeholder paths with the absolute paths to your uv installation and the Linear Regression project directory. It should look like this:

{
    "mcpServers":
    {
        "linear-regression": 
        {
            "command": "ABSOLUTE/PATH/TO/.local/bin/uv",
            "args":
            [
                "--directory",
                "ABSOLUTE/PATH/TO/YOUR-LINEAR-REGRESSION-REPO", 
                "run",
                "server.py"
            ] 
        }
    }
}

Once the file is saved, restart Claude Desktop to link with the MCP server.

Available Tools

The following tools are available in this project to help you work with the dataset and train the model:

Tool	Description	Arguments
`upload_file(path)`	Uploads a CSV file and stores it for processing.	`path`: Absolute path to the CSV file.
`get_columns_info()`	Retrieves the column names in the uploaded dataset.	No arguments.
`check_category_columns()`	Checks for any categorical columns in the dataset.	No arguments.
`label_encode_categorical_columns()`	Label encodes categorical columns into numerical values.	No arguments.
`train_linear_regression_model(output_column)`	Trains a linear regression model and calculates RMSE.	`output_column`: The name of the target column.

Open for Contributions

I welcome contributions to this project! Whether it's fixing bugs, adding new features, or improving the documentation, feel free to fork the repository and submit pull requests.

If you have any suggestions or feature requests, open an issue, and I'll be happy to discuss them!