Website Auditor MCP

Run a full audit

run_audit

Read-only

Run a full website audit to uncover AI visibility, SEO, security, broken links, and performance issues. Receive a scored category summary and a link to the detailed report.

Instructions

Run a full one-time audit of a website — AI visibility plus SEO, security headers, broken links, and performance. Use this when someone asks to "audit," "scan," "check," or "review" a website's health or SEO, or wants a complete report rather than just the AI-visibility number. Returns a scored summary across categories and a link to the full report. The ranked cited-sources evidence behind the AI-visibility number is returned by get_ai_visibility, not by this tool. If name_warning is present, the business name the AI-visibility score was measured against could not be verified — relay that caveat rather than presenting the score as settled fact. Requires a Website Auditor subscription ($10/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

TableJSON Schema

Name	Required	Description
`domain`	Yes	The website domain, e.g. "example.com".
`business_name`	No	Optional. The business's real name, if you know it. Leave it out and the audit detects the name from the site and flags it when unverified — a guessed name is scored as if confirmed, so supply one only when it is actually known.
`business_location`	No	Optional. The city the business trades in, e.g. "Hilo, HI". Leave it out and the audit detects it; when nothing is detectable the questions widen to the country or drop the place entirely, which is right for a national or global business and wrong for a local one.

Output Schema

TableJSON Schema

Name	Required	Description
`scores`	Yes
`report_url`	Yes
`top_issues`	Yes
`name_warning`	No	Set ONLY when the business name could not be verified, which puts the AI-visibility score in question.

Schema Changelog

Changes observed during successful MCP inspections.

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": {
+    "name_warning": {
+      "description": "Set ONLY when the business name could not be verified, which puts the AI-visibility score in question.",
+      "type": "string"
+    },
+    "report_url": {
+      "type": "string"
+    },
+    "scores": {
+      "additionalProperties": true,
+      "properties": {
+        "ai_visibility": {
+          "type": [
+            "number",
+            "null"
+          ]
+        },
+        "performance": {
+          "type": [
+            "number",
+            "null"
+          ]
+        },
+        "security": {
+          "type": [
+            "number",
+            "null"
+          ]
+        },
+        "seo": {
+          "type": [
+            "number",
+            "null"
+          ]
+        }
+      },
+      "required": [
+        "ai_visibility",
+        "seo",
+        "security",
+        "performance"
+      ],
+      "type": "object"
+    },
+    "top_issues": {
+      "items": {
+        "additionalProperties": true,
+        "properties": {
+          "details": {
+            "type": "string"
+          },
+          "module": {
+            "type": "string"
+          },
+          "name": {
+            "type": "string"
+          },
+          "recommendation": {
+            "type": "string"
+          },
+          "severity": {
+            "type": "string"
+          },
+          "url": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "severity"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "scores",
+    "top_issues",
+    "report_url"
+  ],
+  "type": "object"
+}

Changed2 schema fields changedv1.0.15Aug 8, 2026

addedInput schema / properties / business_location

Added value: +{
+  "description": "Optional. The city the business trades in, e.g. \"Hilo, HI\". Leave it out and the audit detects it; when nothing is detectable the questions widen to the country or drop the place entirely, which is right for a national or global business and wrong for a local one.",
+  "type": "string"
+}

addedInput schema / properties / business_name

Added value: +{
+  "description": "Optional. The business's real name, if you know it. Leave it out and the audit detects the name from the site and flags it when unverified — a guessed name is scored as if confirmed, so supply one only when it is actually known.",
+  "type": "string"
+}

First observedv1.0.6Jul 29, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Beyond the readOnly/opennWorld/dstructive annotations, the description discloses the paid-subscription requirement, trial terms, the scored-summary + report-link return shape, and the `name_warning` caveat the agent must relay. It also clarifies this is a one-time audit rather than ongoing monitoring, which is useful operational context.

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

Conciseness5/5

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

Every sentence adds distinct value: purpose, trigger use cases, return format, what is not returned, caveat, and billing/alternative. Core purpose is front-loaded in the first sentence and the operational notes are grouped logically, with no filler or redundant schema repetition.

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?

The output schema covers return structure/fields, so the description only needs to cover invocation, subscription gating, caveat handling, and sibling routing — and it does all four. For a billing-gated tool with many siblings, nothing essential is missing.

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

Parameters3/5

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

Schema coverage is 100% and the schema already explains domain, business_name, and business_location thoroughly, including the unverified-name caveat and location-detection behavior. The description adds little beyond reinforcing the `name_warning` caveat, so the baseline 3 is appropriate.

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?

Opens with a concrete verb and resource: 'Run a full one-time audit of a website' and lists exactly what is covered (AI visibility, SEO, security headers, broken links, performance). It also differentiates itself from get_ai_visibility by clarifying this is the complete-report tool, which makes sibling distinction immediate.

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?

Explicitly spells out trigger phrases ('audit,' 'scan,' 'check,' 'review') and the complete-report use case. It also routes non-subscribers to get_sample_audit and states that cited-source evidence belongs to get_ai_visibility, not this tool — so the agent knows both when and when not to use it.

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

Deploy Server