AI agents call scan_project_structure to retrieve information from SAST MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name suggests this tool reads and analyzes a project's file/directory structure without modifying anything. However, the description is empty, so we cannot confirm there are no side effects. Given the context of a SAST server focused on security scanning (which are generally read-only analysis operations), Read is the most likely category. Confidence is lowered due to the empty description.
From the tool's definition Tool name 'scan_project_structure' and empty description; name implies reading/analyzing directory/file structure
Documented attack patterns abuse exactly the kind of access scan_project_structure gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SAST MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for scan_project_structure:
{
"version": "1",
"default": "deny",
"tools": {
"scan_project_structure": {}
}
}scan_project_structure is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
scan_project_structure. It is categorised as a Read tool in the SAST MCP Server MCP Server, which means it retrieves data without modifying state.
Register the SAST MCP Server MCP server in PolicyLayer and add a rule for scan_project_structure: 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 SAST MCP Server. Nothing to install.
scan_project_structure 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 scan_project_structure 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 scan_project_structure. 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.
scan_project_structure is provided by the SAST MCP Server MCP server (sengtocxoen/sast-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from SAST MCP Server, 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.
39 SAST MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.