zahori_probe · Zahori MCP: Risk & Policy

WHAT IT DOES

What zahori_probe does on Zahori

AI agents invoke zahori_probe to trigger actions in Zahori. 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 zahori_probe needs a policy

This tool performs browser-driven execution against a target URL, loading the page, intercepting media requests, and detecting interactive elements (play/consent buttons). It is not a passive read of stored data — it triggers external browser operations whose effects depend on the URL argument. This places it in the Execute category.

From the tool's definition 'Open a page and gather everything needed to author a profile: media requests seen, iframes, play/consent elements' — the tool actively opens/drives a browser to a web page, observing network requests and interacting with page elements

Risk signalsBulk/mass operation — affects multiple targets

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

zahori_probe Rate-limited

zahori_probe 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": {
    "zahori_probe": {
      "limits": [
        {
          "counter": "zahori_probe_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 Zahori, so you can run agents against it safely.

FAQ

Questions about zahori_probe

What does the zahori_probe tool do? +

Open a page and gather everything needed to author a profile: media requests seen, iframes, play/consent elements, and whether the generic flow already works. Use this before proposing a profile for a new site. It is categorised as a Execute tool in the Zahori MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on zahori_probe? +

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

What risk level is zahori_probe? +

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

Can I rate-limit zahori_probe? +

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

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

zahori_probe is provided by the Zahori MCP server (josesepulvedapino/zahori). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.