// SCAN REPORT

Zahori

6 tools. 4 can modify or destroy data without limits.

4 write tools that can modify data. Rate limits recommended.

Last updated: 10 Jul 2026

4 can modify or destroy data

2 read-only

6 tools total

Community server · catalogue entry checked 10/07/2026

How to control Zahori ↓

TOOL MAP

What Zahori exposes to your agents

Read (2) Write / Execute (4) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Zahori tools

Execute · Medium zahori_probe This tool performs browser-driven execution against a target URL, loading the page, intercepting media requests, and detecting interactive elements (play/consent buttons). Execute · Medium zahori_test_profile The tool actively runs a profile (browser-driven automation) against a target URL, which constitutes executing external operations. Execute · Medium zahori_validate This tool executes an external validation process: it fetches a stream URL, decodes media, and analyzes audio/length. Write · Medium zahori_save_profile This tool creates or modifies data (profile files) in a reversible manner.

4 of Zahori's 6 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Zahori

PolicyLayer is an MCP gateway — it sits between your AI agents and Zahori, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "zahori_save_profile": {
    "limits": [
      {
        "counter": "zahori_save_profile_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "zahori_get": {
    "limits": [
      {
        "counter": "zahori_get_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Zahori — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON ZAHORI →

Instant setup, no code required.

FULL CATALOGUE

All 6 Zahori tools

EXECUTE 3 tools

Execute zahori_probe Open a page and gather everything needed to author a profile: media requests seen, iframes, play/consent eleme Execute zahori_test_profile Run a candidate profile against a URL and grade the result with the oracle. ok=true only when a stream was cap Execute zahori_validate Run the oracle on a resolved stream (url + headers) to check it is real media (decodes, has real audio, plausi

WRITE 1 tools

Write zahori_save_profile Persist a profile so later runs are instant and free. Saves to the project (.zahori/profiles, committable) by

READ 2 tools

Read zahori_get Resolve the media stream behind a page URL using saved profiles or the built-in generic flow. Returns the stre Read zahori_list_profiles List the profiles saved on this machine and in the current project.

FAQ

Questions about Zahori

How do I prevent bulk modifications through Zahori? +

The Zahori server has 1 write tools including zahori_save_profile. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Zahori.

How many tools does the Zahori MCP server expose? +

6 tools across 2 categories: Read, Write. 2 are read-only. 4 can modify, create, or delete data.

How do I enforce a policy on Zahori? +

Register the Zahori MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Zahori tool call.

Deterministic rules across all 6 Zahori tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON ZAHORI →

Instant setup, no code required.

6 Zahori tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Zahori's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →