read existing files from the project directory to see what findings and data have been saved
AI agents call get_project_directory_files to retrieve information from PentestMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though get_project_directory_files only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
read existing files from the project directory to see what findings and data have been saved. It is categorised as a Read tool in the PentestMCP MCP Server, which means it retrieves data without modifying state.
Register the Pentest MCP server in PolicyLayer and add a rule for get_project_directory_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 PentestMCP. Nothing to install.
get_project_directory_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 get_project_directory_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 get_project_directory_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.
get_project_directory_files is provided by the Pentest MCP server (youssefsahnoun/pentestmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.