지정된 디렉토리의 do 파일 목록 조회
AI agents call browse_do_files to retrieve information from Stata MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays information about Stata .do files in a directory without modifying, executing, or deleting any data. It performs a non-destructive query operation typical of file browser functionality, placing it squarely in the Read category with low severity since the blast radius of misuse is limited to information disclosure about file names and metadata.
From the tool's definition Tool description states "do 파일 목록 조회" (retrieves list of do files in specified directory). The name "browse_do_files" and sibling tools (read_do_file, edit_do_file, write_do_file, run_do_file) confirm this is a directory listing/query operation.
Attacks that exploit this kind of access
지정된 디렉토리의 do 파일 목록 조회. It is categorised as a Read tool in the Stata MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Stata MCP Server MCP server in PolicyLayer and add a rule for browse_do_files: 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 MCP Server. Nothing to install.
browse_do_files is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the browse_do_files 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 browse_do_files. 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.
browse_do_files is provided by the Stata MCP Server MCP server (mkprevo/stata-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →