在最近的 Stata MCP session_id 对应的 Stata GUI 中执行一条或多条 Stata 命令；可先用 stata_session(action=
AI agents invoke stata_run to trigger actions in Stata. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool runs commands in a live Stata session, which can perform data transformations, calculations, file I/O, and other operations whose effects depend on the command arguments. While not inherently destructive (Stata commands could theoretically be read-only), the tool's purpose is command execution with potential to modify state, load/save files, and trigger external operations.
From the tool's definition Tool name 'stata_run' and description indicate it 'executes one or more Stata commands' in a Stata GUI session. Execution of arbitrary statistical commands with side effects on data and environment.
Documented attack patterns abuse exactly the kind of access stata_run gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Stata, and nothing reaches the server without passing your rules. This is the rule we recommend for stata_run:
{
"version": "1",
"default": "deny",
"tools": {
"stata_run": {
"limits": [
{
"counter": "stata_run_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}stata_run stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
在最近的 Stata MCP session_id 对应的 Stata GUI 中执行一条或多条 Stata 命令；可先用 stata_session(action=. It is categorised as a Execute tool in the Stata MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Stata MCP server in PolicyLayer and add a rule for stata_run: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Stata. Nothing to install.
stata_run is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the stata_run rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for stata_run. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
stata_run is provided by the Stata MCP server (shichengg/stata-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Stata, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
12 Stata tools catalogued and risk-classified — across an index of 43,000+ MCP servers.