Website Auditor MCP

Start/stop monitoring

track_site

Destructive

Start or stop weekly monitoring of a website's AI visibility so you can track changes and get alerts over time.

Instructions

Start (or stop) ongoing monitoring of a website's AI visibility on a schedule. Use this when someone wants to "monitor," "track," "watch," or "get alerted about" a site's AI visibility over time, rather than a one-off check. Adds weekly re-audits to the history that get_changes reads from — a history every audit already accrues, tracked or not — so use this to be watched on a schedule, not to make get_changes work. Passing enabled: false stops monitoring by deleting the enrollment, as untrack_site does. Requires a Website Auditor subscription ($49/month; eligible new customers get a 7-day free trial — payment method required, no charge until the trial ends) — if the user doesn't have one, call get_sample_audit first to show them the exact output format, free and with no API key.

Input Schema

Name	Required	Description	Default
`domain`	Yes	The website domain, e.g. "example.com".
`cadence`	No	Monitoring cadence (weekly).	weekly
`enabled`	No	Set false to stop monitoring.

Output Schema

Name	Required	Description
`domain`	Yes
`cadence`	No
`created`	No	Present when starting: whether this call created a new tracking.
`message`	Yes
`removed`	No	Present when stopping.
`tracking`	Yes	True after a start/confirm; false after a stop.
`dashboard`	No
`already_tracked`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv1.0.29Nov 5, 2026

addedOutput schema / properties / dashboard

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "note": {
+      "description": "One line naming what the page shows; the same text is in summary where a reply has one.",
+      "type": "string"
+    },
+    "url": {
+      "description": "The member's own dashboard page.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "url",
+    "note"
+  ],
+  "type": "object"
+}

Changed1 schema field changedv1.0.23Sep 9, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "already_tracked": {
+      "type": "boolean"
+    },
+    "cadence": {
+      "type": "string"
+    },
+    "created": {
+      "description": "Present when starting: whether this call created a new tracking.",
+      "type": "boolean"
+    },
+    "domain": {
+      "type": "string"
+    },
+    "message": {
+      "type": "string"
+    },
+    "removed": {
+      "description": "Present when stopping.",
+      "type": "boolean"
+    },
+    "tracking": {
+      "description": "True after a start/confirm; false after a stop.",
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "domain",
+    "tracking",
+    "message"
+  ],
+  "type": "object"
+}

First observedv1.0.6Jul 29, 2026

TDQS

A4.8/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the destructiveHint=true annotation, the description discloses what is actually destroyed — passing enabled:false deletes the enrollment — and that weekly re-audits accumulate into history. It also surfaces the hard prerequisite (Website Auditor subscription, $49/month, payment method required, 7-day trial) that gates a successful call.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The primary action, the trigger conditions, and the subscription prerequisite are front-loaded and easy to scan. The get_changes clause is noticeably convoluted ('a history every audit already accrues, tracked or not'), but it prevents a plausible misuse, so it earns its space even if it could be tightened.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description needn't explain return values, and it covers everything else an agent needs: the trigger, the stop semantics, the destructive consequence, the sibling equivalent, and the paywall fallback. Nothing material for correct invocation is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, but the description adds real consequence-level meaning the schema lacks: enabled:false deletes the enrollment rather than merely pausing it, and that outcome matches untrack_site. Cadence is only weakly enriched (weekly re-audits), leaving the sole enum value mostly to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence gives a specific verb pair (start/stop), the resource (ongoing monitoring of a website's AI visibility), and the scope (on a schedule). It distinguishes itself from the one-off path by naming the contrast with 'a one-off check,' which separates it from run_audit without requiring the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit trigger vocabulary ('monitor,' 'track,' 'watch,' 'get alerted about') and an explicit exclusion ('not to make get_changes work') tell the agent both when and when-not to call it. It also names untrack_site as the equivalent stop path and prescribes a fallback (get_sample_audit) when the user lacks a subscription.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.