Stata-MCP

Let LLM help you achieve your regression with Stata.

Statement: All the documents are generated by AI, except Usage.md which is written by the author.

Quickly Start

Requirements: uv or python 3.11+
If you don't have uv but python, you can install it with pip install uv.

First, you should check whether your device is supported by stata-mcp.

uvx stata-mcp --usable

If each check is passed, you can start using stata-mcp.
If remind not found STATA_CLI, you can see StataFinder to solve it.

The common configuration file (json)

{
  "mcpServers":{
    "stata-mcp": {
      "command": "uvx",
      "args": ["stata-mcp"]
    }
  }
}

We recommend using Stata-MCP with Claude Code for its excellent agentic capabilities.

Before using it, please make sure you have Claude Code installed. If you don't know how to install it, visit GitHub.

Open your terminal, cd to your working directory, and run:

claude mcp add stata-mcp --env STATA_MCP_CWD=$(pwd) --scope project -- uvx --directory $(pwd) stata-mcp

This will create a .mcp.json file in your working directory with the MCP configuration.

Paper Replication: Replicate empirical studies from economics papers
Quick Hypothesis Testing: Validate economic hypotheses through regression analysis
Stata Learning Assistant: Learn econometrics with step-by-step Stata explanations
Code Organization: Review and optimize existing Stata do-files
Result Interpretation: Understand complex statistical outputs and regression results

For detailed usage guide, visit agents/claude_code.md.

If you want to explore more clients or agents, visit their respective documentation.