rescan · Ariadne MCP: Risk & Policy

WHAT IT DOES

What rescan does on Ariadne

AI agents invoke rescan to trigger actions in Ariadne. 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 rescan needs a policy

This tool initiates a re-scan/re-indexing process of the Ariadne service graph, which is an active operation with side effects (rebuilding the index). It doesn't merely read data; it triggers execution of an indexing pipeline. The description is brief and somewhat uninformative about full scope, lowering confidence slightly.

From the tool's definition 'Refresh the Ariadne index from inside the conversation' — triggers an external indexing/scanning operation

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

rescan Rate-limited

rescan 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": {
    "rescan": {
      "limits": [
        {
          "counter": "rescan_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 Ariadne, so you can run agents against it safely.

FAQ

Questions about rescan

What does the rescan tool do? +

Refresh the Ariadne index from inside the conversation. Call this. It is categorised as a Execute tool in the Ariadne MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on rescan? +

Register the Ariadne MCP server in PolicyLayer and add a rule for rescan: 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 Ariadne. Nothing to install.

What risk level is rescan? +

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

Can I rate-limit rescan? +

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

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

rescan is provided by the Ariadne MCP server (whyy9527/ariadne). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.