Scan directory for malware with YARA rules. Returns only files with matches. Uses bundled signature-base rules by default.
AI agents call yara_scan_directory to retrieve information from Windows Forensics MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool executes pattern matching against files using static signatures (YARA rules) to identify potentially malicious content. While it involves rule evaluation, it is fundamentally a forensic analysis and detection tool that retrieves and reports findings without modifying, executing, or deleting any data. It has no side effects on the scanned files or system state.
From the tool's definition Tool performs scanning and pattern matching ('Scan directory for malware with YARA rules') that returns results without modifying the target system. YARA is a read-only pattern analysis tool that generates reports on files matching signatures.
Documented attack patterns abuse exactly the kind of access yara_scan_directory gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Windows Forensics MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for yara_scan_directory:
{
"version": "1",
"default": "deny",
"tools": {
"yara_scan_directory": {}
}
}yara_scan_directory 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 directory for malware with YARA rules. Returns only files with matches. Uses bundled signature-base rules by default. It is categorised as a Read tool in the Windows Forensics MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Windows Forensics MCP Server MCP server in PolicyLayer and add a rule for yara_scan_directory: 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 Windows Forensics MCP Server. Nothing to install.
yara_scan_directory 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 yara_scan_directory 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 yara_scan_directory. 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.
yara_scan_directory is provided by the Windows Forensics MCP Server MCP server (x746b/winforensics-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Windows Forensics 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.
61 Windows Forensics MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.