nuclei_scan · Nuclei MCP: Risk & Policy

WHAT IT DOES

What nuclei_scan does on Nuclei

AI agents invoke nuclei_scan to trigger actions in Nuclei. 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 nuclei_scan needs a policy

Nuclei is an active vulnerability scanner that executes network probes, HTTP requests, and exploit attempts against target systems. Even though the tool description is empty, the server context makes clear this tool triggers external scanning operations against targets.

From the tool's definition Tool name 'nuclei_scan' combined with server description: 'runs scans' using Nuclei (a vulnerability scanner that sends active probes to targets). The server description explicitly mentions 'running scans' against targets.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

nuclei_scan Rate-limited

nuclei_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": {
    "nuclei_scan": {
      "limits": [
        {
          "counter": "nuclei_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 Nuclei, so you can run agents against it safely.

FAQ

Questions about nuclei_scan

What does the nuclei_scan tool do? +

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

How do I enforce a policy on nuclei_scan? +

Register the Nuclei MCP server in PolicyLayer and add a rule for nuclei_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 Nuclei. Nothing to install.

What risk level is nuclei_scan? +

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

Can I rate-limit nuclei_scan? +

Yes. Add a rate_limit block to the nuclei_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 nuclei_scan completely? +

Set action: deny in the PolicyLayer policy for nuclei_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 nuclei_scan? +

nuclei_scan is provided by the Nuclei MCP server (tobiasguta/nuclei-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.