Collect Shellbags from Registry on a Windows host. 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: Shellbags artifact results as a string or error message.
AI agents call windows_shellbags 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 queries existing forensic data (Windows Registry Shellbags) without modifying, deleting, or executing code. It accepts parameters to filter results and returns artifact data. The 'Collect' verb here means retrieve/query, not create/modify, consistent with Velociraptor's forensic triage design. Shellbags are historical data about directory access, read-only from the user's perspective.
From the tool's definition Tool collects and returns Shellbags artifact data from Windows Registry with no modification capability; description indicates it retrieves forensic artifacts ('Collect Shellbags from Registry') with result fields and client parameters.
Documented attack patterns abuse exactly the kind of access windows_shellbags 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_shellbags:
{
"version": "1",
"default": "deny",
"tools": {
"windows_shellbags": {}
}
}windows_shellbags 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.
Collect Shellbags from Registry on a Windows host. 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: Shellbags 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_shellbags: 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_shellbags 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_shellbags 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_shellbags. 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_shellbags 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.