tmonktmonkCommunityยท2 Agent Skills Included

mcp-stata

Run Stata regressions, audits, and replication checks conversationally

Runs Stata code, do-files, and regressions directly from plain-English requests against a local Stata installation. Audits datasets, exports graphs, checks stored results, and verifies replication and robustness without manual log digging. Guides publication-ready tables, referee responses, and causal inference checks so empirical research moves faster.
npx skills add tmonk/mcp-stata --all -g -y
Available:

Tells your AI agent which Stata skill to route each request to, covering setup, execution, replication, data audits, and publication review across supported clients.

All Skills in This Repository (2)

Pure Emerald Level Indicators

Frequently Asked Questions

FAQPage Schema
How to install mcp-stata?โ–ผ

Run `npx skills add tmonk/mcp-stata --all -g -y` in your terminal to install all Stata skills globally. You also need a licensed local Stata 17+ installation and Python 3.11+.

How to run Stata commands with an AI agent?โ–ผ

Once connected, just ask in plain English, for example to load a dataset and run a regression. The agent executes the code through your local Stata and returns the output, stored results, and logs.

Can mcp-stata help with replication and robustness checks?โ–ผ

Yes. It reruns pipelines, compares specifications, captures logs and stored results, and reports whether a result truly replicates, partly matches, or breaks.

Does mcp-stata work with Claude Code, Cursor, and Codex?โ–ผ

Yes. It supports Claude Code, Codex, Gemini CLI, Cursor, Windsurf, and VS Code through the same MCP server and shared skills.

What if mcp-stata cannot find my Stata installation?โ–ผ

Set the STATA_PATH environment variable to your Stata executable path. The environment-diagnose skill can also pinpoint package, permission, and startup issues automatically.

Related Repositories in Data & Analytics

View All in Data & Analyticsโ†’