ModelsAtlas
Explore
Atlas / MCP servers / sepinetam / Stata

StataCAUTION

mcp/sepinetam/stata-1
MCP server by sepinetam · claude code · claude code plugin · claude code skill · Audited 2026-10-06
⚑ Report / re-scanSource ↗

Stata-MCP: A MCP server for integrating Stata into your agent loop with a safety-first design.

Verdict
CAUTION
Grade
C
Trust score
78 /100
Exposed tools
—
Transport
stdio · streamable-http
License
AGPL-3.0
Stars
263
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

MCP-for-Stata is an safety first open-source MCP server and CLI tool with Skills 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.

[](README.md) [](README.zh-CN.md) [](README.fr.md) [](README.es.md) [](https://github.com/SepineTam/mcp-for-stata/actions/workflows/python-package.yml) [](https://pypi.org/project/stata-mcp/) [](https://pepy.tech/projects/stata-mcp) [](LICENSE) [](https://www.bestpractices.dev/projects/14255) [](h

Read from source at commit 28f74d3556f2OBSERVED · 2026-10-06
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code (pypi)
claude mcp add stata-mcp -- None stata-mcp==1.25.1
03

Trust audit

CAUTIONgrade C · trust 78/100 Install with care. The audit found things worth knowing before you trust its output.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeWARN
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (2 observation(s))
Network
declared (7 observation(s))
Shell
declared (7 observation(s))
Dependencies
pinned
Secrets in source
none-found

Findings (24)

MEDIUMCode injection · code.dynamic_import · CWE-78, CWE-94, CWE-95
src/stata_mcp/utils/doctor.py:201
__import__(package)
MEDIUMCode injection · code.dynamic_import · CWE-78, CWE-94, CWE-95
src/stata_mcp/utils/doctor.py:209
__import__(package)
LOWCode injection · code.dynamic_import · CWE-78, CWE-94, CWE-95
tests/test_release_binaries.py:24
module = importlib.import_module(module_name)
LOWCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
tests/test_diagnostic_logging.py:20
exec(
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
LOWCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
tests/test_diagnostic_logging.py:48
exec(
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
LOWInsecure crypto · crypto.weak_hash · CWE-327, CWE-338
src/stata_mcp/data_info/base.py:331
digest = hashlib.md5(self.bytes_io_data.getvalue()).hexdigest()
LOWInsecure crypto · crypto.weak_hash · CWE-327, CWE-338
src/stata_mcp/utils/installer/addon_source.py:143
blob = hashlib.sha1(f"blob {len(data)}\0".encode() + data).hexdigest()
LOWInsecure crypto · crypto.weak_hash · CWE-327, CWE-338
tests/utils/test_installer_addons.py:303
"sha": hashlib.sha1(b"blob 5\0" + data).hexdigest(),
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
.claude/skills/mcp-smoke-test/scripts/cleanup.sh:12
PROJECT_ROOT="$(cd "${SCRIPT_DIR}/../../../../" && pwd)"
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
.claude/skills/mcp-smoke-test/scripts/prepare_smoke_test.sh:12
PROJECT_ROOT="$(cd "${SCRIPT_DIR}/../../../../" && pwd)"
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
tests/skills/test_stata_audit_skill.py:272
"../../outside",
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
tests/stata/test_do_boundary.py:881
"foo/../../bar",
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
tests/utils/test_installer_addons.py:277
"skills/../../bad",
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
tests/data_info/test_security.py:361
"https://192.168.1.1/data.csv",
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
tests/data_info/test_security.py:374
"https://192.168.1.1/data.csv",
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
tests/data_info/test_security.py:522
data_path="https://192.168.1.1/data.csv",
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
tests/data_info/test_security.py:547
data_path="https://192.168.1.1/data.csv",
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
tests/guard/test_data_path_auditor.py:169
result = auditor.validate_url("https://192.168.1.1/data.csv")
LOWInventory / provenance · mcp.no_tools_extracted · CWE-1104
server.json
Why it matters. the tool list is enumerated at runtime by tools/list, not declared in source
Fix. the page says so rather than showing an empty table
INFOSupply chain · prompt.pipe_to_shell · CWE-829, CWE-1357
README.es.md:107
curl -fsSL https://raw.githubusercontent.com/SepineTam/mcp-for-stata/master/scripts/install.sh | bash
INFOSupply chain · prompt.pipe_to_shell · CWE-829, CWE-1357
README.fr.md:107
curl -fsSL https://raw.githubusercontent.com/SepineTam/mcp-for-stata/master/scripts/install.sh | bash
INFOSupply chain · prompt.pipe_to_shell · CWE-829, CWE-1357
README.md:119
curl -fsSL https://raw.githubusercontent.com/SepineTam/mcp-for-stata/master/scripts/install.sh | bash
INFOSupply chain · prompt.pipe_to_shell · CWE-829, CWE-1357
README.zh-CN.md:111
curl -fsSL https://raw.githubusercontent.com/SepineTam/mcp-for-stata/master/scripts/install.sh | bash
INFOSupply chain · prompt.pipe_to_shell · CWE-829, CWE-1357
docs/claude-plugin.md:153
curl -fsSL https://claude.ai/install.sh | bash

Gates applied: no_behavioural_pass.

Audited 2026-10-06 · audit v0.4.1 · source sha 28f74d3556f2full audit observations/trust-audit/mcp-server/sepinetam__stata-1.json · Report an issue / request a re-scan
04

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-0628f74d3556f2CAUTIONC78first audit
05

Questions

What is the Stata MCP server?

Stata-MCP: A MCP server for integrating Stata into your agent loop with a safety-first design.

Is Stata safe to connect to an agent?

With care. The audit graded it C (78/100) and found 24 things worth knowing before you trust this server, listed below with the exact line each was found on.

What credentials does Stata need?

It reads OPENAI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does Stata run?

It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as stata-mcp.

How current is this page?

The grade is for one exact copy of the source (28f74d3556f2), read on 2026-10-06. The repository is watched and re-audited when it changes.

Advertisement