modelscan_scan · Model Safety MCP: Risk & Policy

WHAT IT DOES

What modelscan_scan does on Model Safety MCP

AI agents invoke modelscan_scan to trigger actions in Model Safety MCP. 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 modelscan_scan needs a policy

The tool runs an external scanning tool (modelscan) against either a local filesystem path or a remote URL, which involves executing a process and potentially downloading remote content. This is an Execute-category action.

From the tool's definition 'Run modelscan against a local path or downloadable URL' — actively executes a scanning process against a file path or downloads and scans a remote URL artifact

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

modelscan_scan Rate-limited

modelscan_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": {
    "modelscan_scan": {
      "limits": [
        {
          "counter": "modelscan_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 Model Safety MCP, so you can run agents against it safely.

FAQ

Questions about modelscan_scan

What does the modelscan_scan tool do? +

Run modelscan against a local path or downloadable URL. It is categorised as a Execute tool in the Model Safety 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 modelscan_scan? +

Register the Model Safety MCP server in PolicyLayer and add a rule for modelscan_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 Model Safety MCP. Nothing to install.

What risk level is modelscan_scan? +

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

Can I rate-limit modelscan_scan? +

Yes. Add a rate_limit block to the modelscan_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 modelscan_scan completely? +

Set action: deny in the PolicyLayer policy for modelscan_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 modelscan_scan? +

modelscan_scan is provided by the Model Safety MCP server (itsalissonsilva/modelsafetymcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.