Parse Prefetch files on a Windows host to identify previously executed programs. Args: client_id: Velociraptor client ID. org_id: Optional Velociraptor org ID for multi-tenant deployments. Fields: Comma-separated list of fields to return. Returns: Prefetch artifact results as a string or error me...
AI agents call windows_execution_prefetch to retrieve information from Velociraptor MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves forensic data from Windows Prefetch artifacts, which are read-only system artifacts that contain historical execution records. There are no side effects, no code execution, no data modification, and no destructive operations. It is purely a data retrieval and analysis function, which places it squarely in the Read category.
From the tool's definition Tool parses existing Prefetch files to identify previously executed programs and returns artifact results. The description explicitly states it performs parsing and identification of historical data without modifying or executing anything.
Documented attack patterns abuse exactly the kind of access windows_execution_prefetch gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Velociraptor MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for windows_execution_prefetch:
{
"version": "1",
"default": "deny",
"tools": {
"windows_execution_prefetch": {}
}
}windows_execution_prefetch 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.
Parse Prefetch files on a Windows host to identify previously executed programs. Args: client_id: Velociraptor client ID. org_id: Optional Velociraptor org ID for multi-tenant deployments. Fields: Comma-separated list of fields to return. Returns: Prefetch artifact results as a string or error message. It is categorised as a Read tool in the Velociraptor MCP MCP Server, which means it retrieves data without modifying state.
Register the Velociraptor MCP server in PolicyLayer and add a rule for windows_execution_prefetch: 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 Velociraptor MCP. Nothing to install.
windows_execution_prefetch 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 windows_execution_prefetch 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 windows_execution_prefetch. 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.
windows_execution_prefetch is provided by the Velociraptor MCP server (mgreen27/mcp-velociraptor). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Velociraptor MCP, 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.
28 Velociraptor MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.