AI agents call get_collection_results 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.
The tool appears to query and return forensic collection results from Velociraptor endpoints. While it is a Read operation (no side effects), severity is elevated to medium because forensic data can contain sensitive information about systems, processes, network connections, and user activity that could be exploited if retrieved without authorization or used to inform further attacks.
From the tool's definition Tool name 'get_collection_results' implies retrieval of previously collected forensic data. Empty description limits certainty, but context (Velociraptor forensic triage bridge) and sibling tools like 'collect_artifact' and 'collect_forensic_triage' suggest…
Documented attack patterns abuse exactly the kind of access get_collection_results 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 get_collection_results:
{
"version": "1",
"default": "deny",
"tools": {
"get_collection_results": {}
}
}get_collection_results 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.
get_collection_results. 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 get_collection_results: 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.
get_collection_results 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_collection_results 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_collection_results. 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_collection_results 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.