mcp-stata
by tmonk·★ 62·Score 46
A Model Context Protocol server for Stata that enables AI agents to execute Stata code, inspect data, and retrieve results.
Overview
The mcp-stata server provides a comprehensive toolkit for empirical researchers to integrate LLM assistance into their Stata workflow. It allows AI agents to execute Stata commands, inspect data structures, retrieve stored results (r()/e()), and view graphs directly within the chat interface. The server is particularly designed for academic research workflows, offering specialized skills for data auditing, replication checks, specification comparisons, and publication quality assurance.
Try asking AI
After installing, here are 4 things you can ask your AI assistant:
When to choose this
Choose this if you're an economist or researcher already using Stata who wants to integrate AI assistance directly into your statistical workflow.
When NOT to choose this
Don't choose this if you don't have a licensed copy of Stata 17+, as the server requires a local installation of proprietary statistical software.
Tools this server exposes
8 tools extracted from the READMEstata_runstata_run(code, is_file=False, background=False, echo=True, as_json=True, trace=False, raw=False, max_output_lines=None, cwd=None, session_id='default', strip_smcl=True, filter_pattern=None, exclude_pattern=None)Execute Stata commands or a .do file
stata_task_statusstata_task_status(task_id, wait=False, timeout=60.0, poll_interval=1.0, tail_lines=0)Query or wait on background task status
stata_controlstata_control(action, id)Control active work (break session or cancel task)
stata_read_logstata_read_log(path, offset=0, max_bytes=262144, tail_lines=0, query=None, before=2, after=2, case_sensitive=False, regex=False, max_matches=50)Read, tail, or search a log file
stata_load_datastata_load_data(source, clear=True, as_json=True, raw=False, max_output_lines=None, session_id='default')Load dataset from various sources (sysuse/webuse/use/path/URL)
stata_inspect_datastata_inspect_data(action, query=None, variables=None, start=0, count=50, session_id='default')Inspect data with describe, codebook, summary, search, list, get, or lint
stata_manage_graphsstata_manage_graphs(action, graph_name=None, format='svg', session_id='default')Manage graphs (list, export, export_all)
stata_get_resultsstata_get_results(session_id='default', include_formatRetrieve stored results (r(), e())
Comparable tools
Installation
Installation
Using the installer script
macOS/Linux:
curl -LsSf https://mcp-stata-install.tdmonk.com/install.sh | bashWindows (PowerShell):
irm https://mcp-stata-install.tdmonk.com/install.ps1 | iexClaude Desktop Configuration
Add to your Claude Desktop configuration:
{
"mcpServers": {
"mcp-stata": {
"command": "uvx",
"args": [
"--refresh",
"--refresh-package",
"mcp-stata",
"--from",
"mcp-stata@latest",
"mcp-stata"
]
}
}
}Prerequisites: Stata 17+, Python 3.11+, and uv (recommended).
FAQ
- What version of Stata is required?
- Stata 17+ (Stata MP, SE, or BE) is required. It must be licensed and installed locally.
- How does the server find my Stata installation?
- The server attempts automatic discovery of your Stata installation (supporting standard paths and StataNow). If auto-discovery fails, you can set the STATA_PATH environment variable to your Stata executable.
Compare mcp-stata with
Last updated · Auto-generated from public README + GitHub signals.