Enables an agent to execute Stata do scripts or inline commands locally and retrieve structured results including status, error diagnostics, and output text for consumption by the model.
SaferSkills independently audited Stata Executor MCP (MCP Server) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
stata_executor 是一个面向 Agent 的本地 Stata 执行 MCP server,让 Agent 具备运行 do 脚本/内联命令并读取稳定执行结果的能力。
它返回两类信息:一类是稳定的执行事实,另一类是可直接给模型消费的干净实证结果正文。它不负责解释经济学或实证结果。
uv syncstata_executor 通过 MCP 启动 JSON 的 env 字段注入环境变量:
STATA_EXECUTOR_STATA_EXECUTABLE: Stata 可执行文件路径(必填)STATA_EXECUTOR_EDITION: 版本(可选,mp / se / be,默认 mp)示例:
{
"mcpServers": {
"stata-executor": {
"command": "D:/Developments/PythonProject/Stata-Executor-MCP/.venv/Scripts/python.exe",
"args": ["-m", "stata_executor"],
"cwd": "D:/Developments/PythonProject/Stata-Executor-MCP",
"env": {
"STATA_EXECUTOR_STATA_EXECUTABLE": "D:/Program Files/Stata17/StataMP-64.exe",
"STATA_EXECUTOR_EDITION": "mp"
}
}
}
}启动命令:python -m stata_executor。
doctor: 检查环境与配置run_do: 执行现有的 .do 文件run_inline: 执行单条或多条 inline 命令run_do / run_inline 返回的结构化内容 (structuredContent) 包含以下字段:
status: 执行状态 (succeeded, failed)error_kind: 失败时的错误分类(bootstrap_error / input_error / timeout / stata_parse_or_command_error / stata_runtime_error / artifact_collection_error),成功时为 nullresult_text: 过滤命令回显后的完整结果正文,面向模型直接消费diagnostic_excerpt: 失败时围绕末次命令与错误行的诊断片段artifacts: 本次执行新增或变更的产物绝对路径列表doctor 返回:
ready: 配置与可执行文件是否就绪errors: 未就绪时的错误清单(就绪时为空列表)执行失败时响应的 isError=true 且仍然返回完整 structuredContent,便于 Agent 基于诊断字段进行恢复。
python -m unittest discover -s tests -v~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.