request_rescan · Assetcache MCP: Risk & Policy

WHAT IT DOES

What request_rescan does on Assetcache

AI agents invoke request_rescan to trigger actions in Assetcache. 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 request_rescan needs a policy

This tool triggers a rescan/re-indexing operation on assets. It executes an external process (re-analysis/re-labeling pipeline) rather than simply reading data or writing/modifying stored records. The blast radius is medium because triggering a full rescan of all assets could be resource-intensive and cause system load, but it does not irreversibly delete or modify data.

From the tool's definition '재분석을 트리거한다' (triggers re-analysis/rescan of specific pack/asset or entire library)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

request_rescan Rate-limited

request_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": {
    "request_rescan": {
      "limits": [
        {
          "counter": "request_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 Assetcache, so you can run agents against it safely.

FAQ

Questions about request_rescan

What does the request_rescan tool do? +

특정 팩/자산 또는 전체의 재분석을 트리거한다. It is categorised as a Execute tool in the Assetcache MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on request_rescan? +

Register the Assetcache MCP server in PolicyLayer and add a rule for request_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 Assetcache. Nothing to install.

What risk level is request_rescan? +

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

Can I rate-limit request_rescan? +

Yes. Add a rate_limit block to the request_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 request_rescan completely? +

Set action: deny in the PolicyLayer policy for request_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 request_rescan? +

request_rescan is provided by the Assetcache MCP server (v0o0v/assetcache-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.