start_scan · Greenbone MCP: Risk & Policy

WHAT IT DOES

What start_scan does on GreenboneMCP

AI agents invoke start_scan to trigger actions in GreenboneMCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why start_scan needs a policy

Starting a vulnerability scan is an Execute action—it triggers an external security scanning operation whose effects (network traffic, resource consumption, detection of vulnerabilities) depend on the scan parameters and target arguments. It is not Read (no data retrieval), Write (not a reversible data modification), Destructive (no data deletion), Financial (no money movement), or other.

From the tool's definition Tool name is 'start_scan' on a server explicitly described as enabling 'scan creation' and 'vulnerability scanning workflows'.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_scan Rate-limited

start_scan 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.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches GreenboneMCP, so you can run agents against it safely.

FAQ

Questions about start_scan

What does the start_scan tool do? +

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

How do I enforce a policy on start_scan? +

Register the Greenbone MCP server in PolicyLayer and add a rule for start_scan: 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 GreenboneMCP. Nothing to install.

What risk level is start_scan? +

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

Can I rate-limit start_scan? +

Yes. Add a rate_limit block to the start_scan 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 start_scan completely? +

Set action: deny in the PolicyLayer policy for start_scan. 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 start_scan? +

start_scan is provided by the Greenbone MCP server (matteocolazilli/greenbonemcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.