reanalyze_asset · Picsha AI MCP Server MCP: Risk & Policy

WHAT IT DOES

What reanalyze_asset does on Picsha AI MCP Server

AI agents invoke reanalyze_asset to trigger actions in Picsha AI MCP Server. 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 reanalyze_asset needs a policy

Triggering re-analysis is an Execute action—it runs code/processes (AI analysis pipeline) with side effects that update asset metadata. However, it is not Destructive (data is not deleted or irreversibly overwritten), not Write (it's not creating or modifying user data directly, but running a system operation), and not Financial.

From the tool's definition Tool performs 'manually trigger AI re-analysis' which executes external AI processing logic on an asset. This is a computational operation whose effects (detection results, metadata updates) depend on the asset selected and system state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

reanalyze_asset Rate-limited

reanalyze_asset 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": {
    "reanalyze_asset": {
      "limits": [
        {
          "counter": "reanalyze_asset_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 Picsha AI MCP Server, so you can run agents against it safely.

FAQ

Questions about reanalyze_asset

What does the reanalyze_asset tool do? +

Manually trigger AI re-analysis on an existing asset to detect faces, objects, etc. It is categorised as a Execute tool in the Picsha AI MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on reanalyze_asset? +

Register the Picsha AI MCP Server MCP server in PolicyLayer and add a rule for reanalyze_asset: 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 Picsha AI MCP Server. Nothing to install.

What risk level is reanalyze_asset? +

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

Can I rate-limit reanalyze_asset? +

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

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

reanalyze_asset is provided by the Picsha AI MCP Server MCP server (picsha-ai/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.