scan_url · Sekrd Security Scanner MCP: Risk & Policy

WHAT IT DOES

What scan_url does on Sekrd Security Scanner

AI agents invoke scan_url to trigger actions in Sekrd Security Scanner. 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 scan_url needs a policy

The tool actively initiates a security scan against an external URL, which constitutes executing an external operation with side effects on third-party infrastructure. Misuse could result in unauthorized scanning of systems, potential legal liability, or triggering security defenses at target systems.

From the tool's definition "Run a full security scan on a URL" and "Takes 10-30 seconds" indicate an active external operation is triggered against a target URL, not merely a read/query of existing data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

scan_url Rate-limited

scan_url 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": {
    "scan_url": {
      "limits": [
        {
          "counter": "scan_url_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 Sekrd Security Scanner, so you can run agents against it safely.

FAQ

Questions about scan_url

What does the scan_url tool do? +

Run a full security scan on a URL. Returns score, verdict (SHIP/BLOCK), findings, and fix prompts. Takes 10-30 seconds. It is categorised as a Execute tool in the Sekrd Security Scanner MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on scan_url? +

Register the Sekrd Security Scanner MCP server in PolicyLayer and add a rule for scan_url: 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 Sekrd Security Scanner. Nothing to install.

What risk level is scan_url? +

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

Can I rate-limit scan_url? +

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

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

scan_url is provided by the Sekrd Security Scanner MCP server (sekrdcom/sekrd-mcp-ts). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.