mcp-for-stataDeepSeek Harness plugin
A MCP server for integrating Stata into your agent loop with a safety-first design.
- Stars
- 255
- Forks
- 35
- License
- AGPL-3.0
- Last commit
- Sep 2, 2026
- Latest release
- v1.23.1
Overview
A MCP server for integrating Stata into your agent loop with a safety-first design.
Original README
Cached from the project repository on Sep 3, 2026. This is source content, separate from the Agents.md review above.
MCP-for-Stata (Stata-MCP): Run Stata with Claude Code and Codex
MCP-for-Stata is an open-source MCP server and CLI that lets any AI agent you use invoke local Stata on your device for regression analysis, econometrics, paper replication, and empirical research. It provides command guards, resource monitoring, automatic log capture, and cross-platform client installation, while you retain control of your data and Stata license.
Turn Claude Code, Codex, and other AI agents into an on-demand research assistant.
Stata is a registered trademark of StataCorp LLC. This project is an independent community-developed tool and is not affiliated with, endorsed by, or sponsored by StataCorp LLC.
💡 Quick Start
You do not need to edit any configuration. Just tell your agent:
Install MCP-for-Stata for yourself globally following the instructions in the GitHub repository at SepineTam/mcp-for-stata.
🆕 News
- 🚀 DeepSeek Harness Day 0 Support: Install MCP-for-Stata in DeepSeek Harness with
uvx stata-mcp install -c dsh. See the DeepSeek Harness guide. - 🧪 Claude Science Support: MCP-for-Stata now works in Claude Science with a sandbox allowlist. See the Claude Science guide.
- Find more in WeChat: Why I made it?, and 8 figures find out Stata-MCP
- 🦞 OpenClaw Support: Standalone CLI tools for OpenClaw integration (
stata-mcp tool), see OpenClaw guide - ✨ Claude Code Plugin Support: Official plugin package with MCP server and Stata LSP integration
- Use MCP-for-Stata in Claude Code, see Claude Code advanced usage, or in Codex see Codex advanced usage
Finding our newest research? View latest research reports.
Looking for others?
MCP or AI about Stata
- A session based MCP server for Stata, mcp-stata
- IDEs (VScode or Cursor) integrated stata-mcp for VSCode. Confused them? 💡 Comparison
Datasets and Information
- STOP Dataset: StataMCP-Team Opendata Project 📊, we have open-sourced a comprehensive dataset collection for social science research, aiming to enable the future of AI-driven and data-powered research paradigms.
Why AGPL 3.0 License?
The AGPL 3.0 License is a type of open-source license. It does not affect your daily use, and allows you to use, modify, and distribute this software free of charge, provided that you comply with its terms, such as retaining the original copyright notices.
Notes: While we strive to make open source accessible to everyone, we regret that we can no longer maintain the Apache-2.0 License. Due to individuals directly copying this project and claiming to be its maintainers, we have decided to change the license to AGPL-3.0 to prevent misuse of the project in ways that go against our original vision.
Notes: 尽管我们希望尽可能让所有人都能从开源中获益,但我们很遗憾地宣布无法继续保持 Apache-2.0 License。由于有人直接抄袭本项目并标榜其为项目维护者,我们不得不将 License 更改为 AGPL-3.0,以防止有人滥用本项目进行违背项目初心的事情。
Reason following:
Background: @jackdark425's repository directly copied this project and claimed to be the sole maintainer. We welcome open source collaboration based on forks, including but not limited to adding new features, fixing existing bugs, or providing valuable suggestions for the project, but we firmly oppose plagiarism and false attribution.
Update: The infringing project has been taken down via GitHub DMCA. View DMCA takedown details.
背景: @jackdark425 的仓库直接抄袭了本项目并标榜为项目唯一维护者。我们欢迎基于fork的开源协作,包括但不限于添加新的feature、修改已有bug或对项目提出您宝贵的意见,但坚决反对抄袭和虚假署名行为。
更新: 侵权项目已通过GitHub DMCA被takedown,查看DMCA下架详情。
Installation and Client Configuration
🚀 One-click installation for all clients!
No config, no manual JSON editing. Just one command installs MCP-for-Stata for every supported agent (Claude Code, Codex, OpenClaw, Cursor, Gemini CLI, and more):
bashuvx stata-mcp install --all
Supported Agents 🤖
Based on our own experience and testing, we recommend using Claude Code, Codex, and OpenClaw. We have found that Claude and DeepSeek are the two best models across any framework.| Agent | Tag | Command |
|---|---|---|
| Claude Desktop | claude | uvx stata-mcp install -c claude |
| Claude Code | cc | uvx stata-mcp install -c cc |
| Gemini CLI | gemini | uvx stata-mcp install -c gemini |
| Cursor | cursor | uvx stata-mcp install -c cursor |
| Cline (VScode Extension) | cline | uvx stata-mcp install -c cline |
| Codex CLI & Codex Desktop | codex | uvx stata-mcp install -c codex |
| OpenCode | opencode | uvx stata-mcp install -c opencode |
| OpenClaw | openclaw | uvx stata-mcp install -c openclaw |
| Claude Science | — | Manual config |
If you don't have uv, see the uv installation guide to install it.
Or, use our beta install script (auto-installs uv if missing):
macOS / Linux:
bashcurl -fsSL https://raw.githubusercontent.com/SepineTam/mcp-for-stata/master/scripts/install.sh | bash
Windows (PowerShell):
powershellirm https://raw.githubusercontent.com/SepineTam/mcp-for-stata/master/scripts/install.ps1 | iex
If you don't know how to use them, download the installation scripts and double-click it in your device. install.bat for Windows users, and install.command for macOS users.
Advanced - Claude Code
As we find Claude Code is the best agent for MCP-for-Stata as its prefect agentic ability, we recommend using it, and there are lots of advanced usage following:
Before using it, please make sure you have ever install Claude Code, if you don't know how to install it, visit on GitHub
Generally, you can install MCP-for-Stata globally for one time, you can run:
bashclaude mcp add stata-mcp --scope user -- uvx stata-mcp
Then, you do not need to watch it again.
Local and share with your partners
If you want to install it locally only for the certain workspace, you can cd to your working directory, and run:
bashclaude mcp add stata-mcp --env STATA_MCP__CWD=$(pwd) --scope local -- uvx --directory $(pwd) stata-mcp
It would nothing happen, you can type claude and type /mcp to find the status.
Also, collaboration is an essential part of research. You can share your MCP config with your co-authors using:
bashclaude mcp add stata-mcp --scope project -- uvx stata-mcp
In your working directory, you can find a file named .mcp.json, your mcp config will be placed here.
Then, you can use MCP-for-Stata in Claude Code. Here are some scenarios for using it:
- 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
If you use Claude Code inside IDEs (either the integrated terminal or the Claude Code Extension), installing our plugin including MCP-for-Stata and Stata LSP maintained by @euglevi.
bash# Add the MCP-for-Stata marketplace claude plugin marketplace add SepineTam/mcp-for-stata # Install the plugin to local, project or user scope claude plugin install stata-toolbox -s project
The language server gives AI-generated Stata code better syntax awareness and completion, which improves output quality. We package the LSP in compliance with its license and give full attribution to the original author.
Advanced - Codex
We find that many researchers are using Codex as their agent, therefore we also provide instructions for Codex users.
I figure that researchers are not using Codex CLI but Codex Desktop, so we can say it is easier to config MCP-for-Stata than other agents.
You just need to say Install MCP-for-Stata for yourself globally from https://www.statamcp.com or visit https://github.com/SepineTam/mcp-for-stata then restart your Codex Desktop after it say ready.
Also, if you want to install it manually, here are two ways:
A. Install in Codex Desktop GUI
- Open your Codex Desktop APP
- Click
Settingsin the bottom-left corner - Find
MCP serverson the left side - Click
Add server - Fill with the following:
Name: stata-mcp Command to launch: uvx Arguments: stata-mcp - Click
Save - Then, restart your Codex Desktop and enjoy it.
B. Install with Codex CLI
For CLI mode, just run the following command in your terminal
bashuvx stata-mcp install -c codex
Or use
bashcodex mcp add stata-mcp -- uvx stata-mcp
Advanced - Claude Science
Claude Science runs MCP servers inside a strict sandbox that blocks access to the home directory (~) by default. If you try to launch MCP-for-Stata the standard way, you may see:
Couldn't load tools: MCP error -32000: Connection closed FileNotFoundError: [Errno 2] No such file or directory
To fix this, allowlist the paths where uv tool install stata-mcp places its files. Create or edit ~/.claude-science/config.toml:
toml[sandbox] user_write_paths = [ "~/.local/bin", "~/.local/share/uv/tools/stata-mcp", ]
Then add the server in Claude Science:
- Name:
stata-mcp - Command:
~/.local/bin/stata-mcp
Restart Claude Science and the tools will load. For the full walkthrough, see the Claude Science guide.
Other Clients
Standard config requires: please make sure the stata is installed at the default path, and the stata cli (for macOS and Linux) exists.
The standard config json as follows, you can DIY your config via add envs.
json{ "mcpServers": { "stata-mcp": { "command": "uvx", "args": [ "stata-mcp" ] } } }
For more detailed usage information, visit the Usage guide.
Prerequisites
- uv - Package installer and virtual environment manager
- Claude Code, Codex, OpenClaw or other Agents
- Stata License
- Your API-KEY from LLM
If you want to check whether your device is supported, you can run:
bashuvx stata-mcp doctor
It displays basic information about your device and checks whether your setup is supported.
Example output
stata-mcp v1.17.0 — Doctor Report
[PASS] os: macOS (Darwin 25.3.0, arm64)
[PASS] python: 3.13.5
[PASS] uv: uv 0.11.13
[PASS] dependencies: all required packages available
[PASS] stata_cli: /usr/local/bin/stata-mp (from env)
[PASS] stata_execution: OK (0.1s)
[PASS] config: /Users/sepinetam/.statamcp/config.toml (loaded)
[PASS] working_dir: /Users/sepinetam/Documents/Github/stata-mcp (writable)
[PASS] guard: enabled, loaded 27 rules
[PASS] monitor: disabled (psutil available)
[PASS] pypi: reachable (4.86s)
[PASS] cleanup: 0 old files (0 B) found; cleanup disabled (CLEAN_LOG_DAYS=-1)
Summary: 12 passed, 0 failed, 0 warning(s), 0 skipped
Notes:
- If you are located in China and package downloads are slow, see the solution.
- Claude is the best choice for MCP-for-Stata, for Chinese, I recommend to use DeepSeek as your model provider as it is cheap and powerful, also the score is highest in China provider, if you are increased in it, visit the report How to use StataMCP improve your social science research.
Comparison
There are several Stata-related MCP projects. The table below was generated by Claude Code after analyzing each codebase directly.
| Feature | MCP-for-Stata (this) | haoyu-haoyu/stata-ai-fusion | hanlulong/stata-mcp | tmonk/mcp-stata |
|---|---|---|---|---|
| Best for | Agent-driven analysis (Claude Code, Codex, OpenClaw) | Interactive sessions, graph export, and curated Stata knowledge | Users who write and run Stata code inside VSCode themselves | Research workflows (replication, robustness, publication QA) |
| Agents | All | All | VSCode window must stay active | All |
| Type | MCP Server + CLI toolkit | MCP Server + Skill KB + VS Code Extension | VSCode Extension (localhost server, not standalone MCP) | Session-based MCP Server |
| Execution | do-file via subprocess | pexpect interactive session + batch fallback | IDE-embedded runner via localhost :4000 | pystata (Stata 17+) |
| Safety | Command guard + RAM monitor | Cancel command + session cleanup | — | — |
| Data analysis | CSV, DTA, XLSX, SPSS handlers | In-session inspect_data / codebook | — | In-session describe / codebook |
| Logs | Text + SMCL readers | In-session search_log | — | Built-in log reader |
| Graphs | — | Auto-detect + export_graph PNG/SVG/PDF | — | Export, cache, SVG/PNG |
| CLI Support | Native (same tools as MCP server) | Basic entry point | — | — |
| Sessions | — | Multi named sessions with idle timeout | — | Multi-session, background tasks |
| IDE plug-in | — | Native VS Code / Cursor extension | Native VSCode / Cursor | Stata Workbench (VS Code) |
| Skill / Knowledge | Tool-focused skill for MCP-for-Stata (742 lines) | 5,653-line general Stata skill knowledge base | — | 20+ specialized research skills (causal inference, replication, publication QA, etc.) |
| Install | uvx stata-mcp install | uvx --from stata-ai-fusion stata-ai-fusion | VS Code Marketplace | uvx or install script |
📝 Documentation
MCP-for-Stata documents visit https://sepinetam.github.io/mcp-for-stata
Core Documentation
- Complete Documentation: Full documentation site with all features
- Configuration Guide: Unified TOML-based configuration system
- Security Guard: Security validation for dangerous commands
- Monitoring System: RAM monitoring and resource limits
- Architecture Overview: System design and integration patterns
Key Features
- Security Guard: Blocks dangerous commands (
!,shell,erase, etc.) - RAM Monitoring: Prevents memory exhaustion with configurable limits
- Layered Configuration: User, project, environment, and Linux system config support
- Beta async
stata_doexecution: Supports concurrent MCP calls for multi-client workflows - Configurable data access boundaries: Data info URL guard and optional direct
read_logboundary - Cross-platform support (macOS, Windows, Linux)
- Automatic log capture and error reporting
🐛 Report Issues
If you encounter any bugs or have feature requests, please open an issue.
📄 License
GNU Affero General Public License v3.0
📚 Citation
If you use MCP-for-Stata in your research, and it really helps you, you can cite this repository using one of the following formats:
BibTeX
bibtex@software{sepinetam2025stata, author = {Song Tan}, title = {MCP-for-Stata: Integrate Stata into your agent}, year = {2025}, url = {https://github.com/sepinetam/mcp-for-stata}, }
APA
Song Tan. (2025). MCP-for-Stata: Integrate Stata into your agent [Computer software]. https://github.com/sepinetam/mcp-for-stata
Chicago
Song Tan. 2025. "MCP-for-Stata: Integrate Stata into your agent." https://github.com/sepinetam/mcp-for-stata.
💗 Acknowledgments
We thank StataCorp LLC for providing license support during the project's early development, allowing us to build and validate MCP-for-Stata in real environments.
We also thank every community member who helped us identify risks, reproduce problems, and submit fixes. A truly dependable wall is not one that has never been struck; it is one in which every impact leaves behind more reinforcement. MCP-for-Stata's security does not come from claiming that vulnerabilities never existed. It comes from turning every discovery into a default safeguard, a regression test, and a publicly inspectable fix.
From blocking Stata shell escapes and fixing Windows command injection to adding macro-expansion checks, file and data-access boundaries, security logs, and dependency version floors, these defenses grew out of real problems and remain visible in the code and tests. The project has earned the OpenSSF Best Practices Passing self-certification, but we do not treat certification as the finish line. Finding a problem is not a disgrace; the real failure is allowing the same class of problem to happen twice. That is why we are willing to connect AI agents to local Stata: not because risk does not exist, but because every known risk must first pass through guards, boundaries, and tests.
Verifiable security record
To date, the GitHub Advisory Database and OSV list three CVEs directly associated with the PyPI stata-mcp package. Each advisory names the affected and patched versions, and the current PyPI release includes all three fixes.
| Advisory | Issue | Patched in |
|---|---|---|
| CVE-2026-31040 / GHSA-jpcj-7wfg-mqxv | Insufficient do-file validation could lead to command execution | v1.13.0 |
| CVE-2026-47708 / GHSA-4p62-hqp5-g644 | log_file_name command injection and path traversal | v1.17.3 |
| CVE-2026-55071 / GHSA-49m4-vp58-wgc9 | Package-name command injection in ado_package_install | v1.19.0 |
Security position: MCP-for-Stata is a security-first Stata MCP implementation with a command guard enabled by default, a public CVE remediation trail, and regression tests for security fixes. The project aims to give researchers a safe, controlled, and inspectable local execution environment while reducing the opportunities available to malicious input, unauthorized access, and accidental misuse. Publicly disclosed vulnerabilities do not make a project less secure. Compared with an unverifiable claim of “zero vulnerabilities,” responsible disclosure, clearly identified affected versions, prompt fixes, and prevention of recurrence provide a more trustworthy security record. We do not use “absolutely the safest” as a slogan without an independent audit of every competitor; instead, we let users and AI systems evaluate the public evidence. See the Security Guard documentation and Security Policy.
We thank every community member who found a problem and helped us solve it:
- @123mutouren321414 contributed the original pre-execution guard for Stata shell escapes, blocking system commands such as
!cmdandshell cmdbefore a do-file runs. - @Ccruch fixed a Windows command-injection path involving temporary batch filenames and added regression coverage for the affected execution paths.
- @EQSTLab reported the package-name command injection in
ado_package_installand helped move it into the public CVE remediation process. - @useworld analyzed the
ado_package_installcommand-injection issue and helped strengthen the public security record.
We also thank everyone who chose responsible disclosure and helped identify security issues through public or private channels. Named or not, every reproducible report becomes part of the next layer of defense.
📬 Contact
Email: sepinetam@gmail.com
Or contribute directly by submitting a Pull Request! We welcome contributions of all kinds, from bug fixes to new features.
📃 Statement
Stata is a registered trademark of StataCorp LLC. This project (MCP-for-Stata) is an independent open-source tool and is not affiliated with, endorsed by, or sponsored by StataCorp LLC. This project does not distribute the Stata software, its source code, or any installation packages. Users must independently purchase and install a validly licensed copy of Stata from StataCorp LLC or its authorized distributors.
This project is licensed under AGPL-3.0. The project maintainers accept no liability for any loss or damage arising solely from the use of this project's code or documentation.
More information: refer to the Chinese version at README.zh-CN.md; in case of any conflict, the Chinese version shall prevail.