skvil_scan · Skvil MCP: Risk & Policy

WHAT IT DOES

What skvil_scan does on Skvil

AI agents use skvil_scan to create or update resources in Skvil — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Skvil environment.

WHY IT NEEDS A POLICY

Why skvil_scan needs a policy

The tool submits (writes) security scan results to the Skvil reputation system, creating or updating records on-chain. This is a Write operation as it adds data to the reputation system. While it involves blockchain records described as 'immutable', the act itself is a data submission/creation.

From the tool's definition Submit security scan results for an AI agent skill to the Skvil reputation

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

skvil_scan Rate-limited

skvil_scan stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "skvil_scan": {
      "limits": [
        {
          "counter": "skvil_scan_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about skvil_scan

What does the skvil_scan tool do? +

Submit security scan results for an AI agent skill to the Skvil reputation. It is categorised as a Write tool in the Skvil MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on skvil_scan? +

Register the Skvil MCP server in PolicyLayer and add a rule for skvil_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 Skvil. Nothing to install.

What risk level is skvil_scan? +

skvil_scan is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit skvil_scan? +

Yes. Add a rate_limit block to the skvil_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 skvil_scan completely? +

Set action: deny in the PolicyLayer policy for skvil_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 skvil_scan? +

skvil_scan is provided by the Skvil MCP server (skvil-ia/skvil-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.