Rmcp

🚀 R MCP Server

An R-implemented Model Context Protocol (MCP) server that offers advanced econometric modeling and data analysis capabilities. This server enables AI assistants to seamlessly perform complex econometric and statistical analyses, helping you quickly gain insights from data.

🚀 Quick Start

The R MCP Server is designed to facilitate complex econometric and statistical analyses. It allows AI assistants to interact with the R environment to run various models and tests.

✨ Features

• Linear Regression: Run linear models with optional robust standard errors.
• Panel Data Analysis: Estimate fixed effects, random effects, pooling, between effects, and first-difference models.
• Instrumental Variables: Build and estimate IV regression models.
• Diagnostic Tests: Test for heteroscedasticity, autocorrelation, and model misspecification.
• Descriptive Statistics: Generate summary statistics of datasets using R's summary() function.
• Correlation Analysis: Calculate Pearson or Spearman correlation coefficients between variables.
• Group Aggregation: Group data by specified columns and calculate summary statistics using dplyr.
• Resources: Access reference documentation for various econometric techniques.
• Prompts: Execute common econometric analyses using predefined prompt templates.

📦 Installation

Using Docker (Recommended)

1. Build the Docker image:

   docker build -t r-econometrics-mcp .
   

2. Run the container:

   docker run -it r-econometrics-mcp
   

Manual Installation

Install the required Python packages:

pip install -r requirements.txt

Install the required R packages:

install.packages(c("plm", "lmtest", "sandwich"))

💻 Usage Examples

Basic Usage

The server provides the following tools:

linear_model

Run a linear regression model.

Parameters:

• formula (string): Regression formula (e.g., 'y ~ x1 + x2')
• data (object): Dataset as a dictionary/JSON object
• robust (boolean, optional): Whether to use robust standard errors

panel_model

Run a panel data model.

Parameters:

• formula (string): Regression formula (e.g., 'y ~ x1 + x2')
• data (object): Dataset as a dictionary/JSON object
• index (array): Panel index variables (e.g., ['individual', 'time'])
• effect (string, optional): Effect type: 'individual', 'time', or 'twoways'
• model (string, optional): Model type: 'within', 'random', 'pooling', 'between', or 'fd'

diagnostics

Perform model diagnostics.

Parameters:

• formula (string): Regression formula (e.g., 'y ~ x1 + x2')
• data (object): Dataset as a dictionary/JSON object
• tests (array): Tests to run (e.g., ['bp', 'reset', 'dw'])

iv_regression

Estimate an instrumental variables regression.

Parameters:

• formula (string): Regression formula (e.g., 'y ~ x1 + x2 | z1 + z2')
• data (object): Dataset as a dictionary/JSON object

📚 Documentation

Resources

• econometrics:formulas: Information on common econometric model formulations
• econometrics:diagnostics: Reference for diagnostic tests
• econometrics:panel_data: Guide for panel data analysis

🤝 Contribution

Contributions are welcome! Please feel free to submit a Pull Request.

📄 License

This project is licensed under the MIT License.