collect_artifact

THE RISK

High Risk

Why collect_artifact needs a policy

Velociraptor's 'collect_artifact' operation triggers active data collection on remote endpoints, executing forensic artifact collection jobs. Based on the server context (forensic triage, Windows endpoints) and sibling tool 'collect_forensic_triage', this tool likely initiates remote execution of collection tasks on live systems.

From the tool's definition Tool name 'collect_artifact' on a Velociraptor forensic triage MCP server; description is empty/uninformative.

Documented attack patterns abuse exactly the kind of access collect_artifact gives an agent:

POLICY

How to control collect_artifact

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 collect_artifact:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "collect_artifact": {
      "limits": [
        {
          "counter": "collect_artifact_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

collect_artifact stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register Velociraptor MCP — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Velociraptor MCP tools

Execute collect_forensic_triage Start a Windows.Triage.Targets basic triage collection and return flow metadata. Args Read client_info Retrieve client information from the Velociraptor server. Args: hostname: Hos Read get_collection_results get_collection_results Read linux_groups List groups on a Linux host. Args: client_id: The Velociraptor client ID. Read linux_mounts List mounts on a Linux host. Args: client_id: The Velociraptor client ID. Read linux_netstat_enriched List network connections (netstat) with process metadata on a Linux host. Args: Read linux_pslist List running processes on a Linux host. Args: client_id: The Velociraptor cli Read linux_users List users on a Linux host. Args: client_id: The Velociraptor client ID.

All 28 Velociraptor MCP tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Velociraptor MCP → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about collect_artifact

What does the collect_artifact tool do? +

collect_artifact. It is categorised as a Execute tool in the Velociraptor MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on collect_artifact? +

Register the Velociraptor MCP server in PolicyLayer and add a rule for collect_artifact: 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.

What risk level is collect_artifact? +

collect_artifact is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit collect_artifact? +

Yes. Add a rate_limit block to the collect_artifact 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.

How do I block collect_artifact completely? +

Set action: deny in the PolicyLayer policy for collect_artifact. 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.

What MCP server provides collect_artifact? +

collect_artifact 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.

Enforce policy on every Velociraptor MCP tool call.

Start from Velociraptor MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →