Website Auditor MCP

Compare against competitors

compare_competitors

Compare your website's AI visibility against named competitors to see their scores and the ranking gaps where they appear but your site does not.

Instructions

Compare a website's AI visibility head-to-head against named competitors. Use this when someone asks "how do I stack up against X and Y," "who does ChatGPT recommend instead of me," or wants a competitive AI-visibility view. Returns each competitor's score and where they appear that the site does not. Each competitor not already cached costs one audit against your daily quota; if the quota can't cover every competitor, it ranks the ones it could audit and returns a quota summary plus a skipped list naming the rest — it never drops competitors silently or invents scores. If the quota is already exhausted it returns an over-quota error with the reset time. 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
`domain`	Yes	The website domain, e.g. "example.com".
`competitors`	Yes	Competitor domains to compare against.
`business_location`	No	Optional. The market to compare within, e.g. "Chiang Mai, Thailand". Applied to the site AND every competitor, because a comparison asks about one market — scoring one locally and the others globally would rank answers to two different questions. Leave it out and each audit detects its own location, which is right for national or global businesses and wrong for local ones.

Output Schema

Name	Required	Description
`gaps`	Yes	Engines where a competitor appears in AI answers and this site does not.
`quota`	Yes
`market`	Yes	The market every audit in this comparison was scored in, or null when each domain's own location was detected.
`ranking`	Yes
`skipped`	Yes
`summary`	Yes
`dashboard`	No
`recommendation_gap`	No	How far behind the competitor you trail most the site is, each side as a share of its own answers, compared on the assistants that answered for both. Present only when both audits recorded stances; its sentence reads the result back in one line.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields 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"
+}

addedOutput schema / properties / recommendation_gap

Added value: +{
+  "additionalProperties": true,
+  "description": "How far behind the competitor you trail most the site is, each side as a share of its own answers, compared on the assistants that answered for both. Present only when both audits recorded stances; its sentence reads the result back in one line.",
+  "properties": {
+    "assistants": {
+      "anyOf": [
+        {
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "The assistants the figures are over: those that answered for both sites. Null when that could not be checked."
+    },
+    "by_competitor": {
+      "items": {
+        "additionalProperties": true,
+        "properties": {
+          "answers": {
+            "type": "number"
+          },
+          "assistants": {
+            "anyOf": [
+              {
+                "items": {
+                  "type": "string"
+                },
+                "type": "array"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "domain": {
+            "type": "string"
+          },
+          "gap_points": {
+            "type": "number"
+          },
+          "recommended": {
+            "type": "number"
+          },
+          "same_questions": {
+            "type": [
+              "boolean",
+              "null"
+            ]
+          },
+          "state": {
+            "enum": [
+              "behind",
+              "level",
+              "ahead"
+            ],
+            "type": "string"
+          },
+          "unverified": {
+            "description": "True when this competitor's business name could not be verified.",
+            "type": "boolean"
+          },
+          "you_answers": {
+            "description": "Your answers on the same basis as this competitor's figures.",
+            "type": "number"
+          },
+          "you_recommended": {
+            "description": "Your recommended answers on the same basis as this competitor's figures.",
+            "type": "number"
+          }
+        },
+        "required": [
+          "domain",
+          "same_questions",
+          "assistants",
+          "state",
+          "gap_points",
+          "recommended",
+          "answers",
+          "you_recommended",
+          "you_answers",
+          "unverified"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "gap_points": {
+      "description": "Positive when the top competitor is recommended more often.",
+      "type": "number"
+    },
+    "not_compared": {
+      "description": "Competitors left out because their audit recorded no stances.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "rival": {
+      "description": "The competitor you trail most (when you lead every competitor, the one you lead least), compared on the assistants that answered for both sites.",
+      "type": "string"
+    },
+    "rival_answers": {
+      "type": "number"
+    },
+    "rival_recommended": {
+      "type": "number"
+    },
+    "same_questions": {
+      "description": "Whether both audits asked the same set of questions; null when either did not record them.",
+      "type": [
+        "boolean",
+        "null"
+      ]
+    },
+    "sentence": {
+      "type": "string"
+    },
+    "state": {
+      "enum": [
+        "behind",
+        "level",
+        "ahead"
+      ],
+      "type": "string"
+    },
+    "tied_with": {
+      "description": "Other competitors with identical counts over the identical basis: one gap, all named.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "you_answers": {
+      "type": "number"
+    },
+    "you_recommended": {
+      "type": "number"
+    }
+  },
+  "required": [
+    "state",
+    "gap_points",
+    "rival",
+    "tied_with",
+    "same_questions",
+    "assistants",
+    "rival_recommended",
+    "rival_answers",
+    "you_recommended",
+    "you_answers",
+    "not_compared",
+    "sentence",
+    "by_competitor"
+  ],
+  "type": "object"
+}

changedOutput schema / properties / skipped / items / properties / reason / description

Previous value: -"\"quota\" | \"unreachable\" | \"error\"."New value: +"\"quota\" | \"unreachable\" | \"time_limit\" | \"error\"."

Changed2 schema fields changedv1.0.23Sep 9, 2026

addedInput schema / properties / business_location

Added value: +{
+  "description": "Optional. The market to compare within, e.g. \"Chiang Mai, Thailand\". Applied to the site AND every competitor, because a comparison asks about one market — scoring one locally and the others globally would rank answers to two different questions. Leave it out and each audit detects its own location, which is right for national or global businesses and wrong for local ones.",
+  "type": "string"
+}

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "gaps": {
+      "description": "Engines where a competitor appears in AI answers and this site does not.",
+      "items": {
+        "additionalProperties": true,
+        "properties": {
+          "competitor": {
+            "type": "string"
+          },
+          "engine": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "engine",
+          "competitor"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "market": {
+      "description": "The market every audit in this comparison was scored in, or null when each domain's own location was detected.",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "quota": {
+      "additionalProperties": true,
+      "properties": {
+        "audits_skipped": {
+          "description": "Competitors skipped because the daily quota ran out.",
+          "type": "number"
+        },
+        "audits_used": {
+          "description": "Fresh audits actually spent by this call.",
+          "type": "number"
+        },
+        "cached_reused": {
+          "description": "Domains served from a recent cached audit; cost no quota.",
+          "type": "number"
+        },
+        "limit": {
+          "type": [
+            "number",
+            "null"
+          ]
+        },
+        "remaining": {
+          "type": [
+            "number",
+            "null"
+          ]
+        },
+        "reset": {
+          "type": [
+            "string",
+            "null"
+          ]
+        }
+      },
+      "required": [
+        "limit",
+        "remaining",
+        "audits_used",
+        "audits_skipped",
+        "cached_reused",
+        "reset"
+      ],
+      "type": "object"
+    },
+    "ranking": {
+      "items": {
+        "additionalProperties": true,
+        "properties": {
+          "domain": {
+            "type": "string"
+          },
+          "note": {
+            "type": "string"
+          },
+          "score": {
+            "type": [
+              "number",
+              "null"
+            ]
+          }
+        },
+        "required": [
+          "domain",
+          "score"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "skipped": {
+      "items": {
+        "additionalProperties": true,
+        "properties": {
+          "detail": {
+            "type": "string"
+          },
+          "domain": {
+            "type": "string"
+          },
+          "reason": {
+            "description": "\"quota\" | \"unreachable\" | \"error\".",
+            "type": "string"
+          }
+        },
+        "required": [
+          "domain",
+          "reason"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "summary": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "ranking",
+    "gaps",
+    "quota",
+    "skipped",
+    "summary",
+    "market"
+  ],
+  "type": "object"
+}

First observedv1.0.6Jul 29, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations only say readOnly=false, destructive=false, openWorld=true; the description adds the material facts an agent needs: each uncached competitor costs one audit against a daily quota, partial results are ranked with a `skipped` list rather than silently dropped, and exhausted quota yields an over-quota error with reset time. It also discloses the paid subscription prerequisite and trial terms, which no annotation conveys.

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?

Front-loaded with purpose and trigger phrases, then behavior, then prerequisites — a sensible ordering with no filler sentences. It is on the long side, and the parenthetical pricing/trial detail ($49/month, 7-day trial, payment method) is verbose, though it is information the agent may need to relay to the user.

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?

An output schema exists, yet the description still frames the result shape at a high level (per-competitor score plus where they appear) and documents the quota and skipped fields that explain partial results. Combined with the subscription gate and the get_sample_audit fallback, nothing an agent needs to call this correctly 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 description coverage is 100%, and the schema itself already explains business_location's market-scoping rationale thoroughly, so the description adds little parameter-level meaning. It does imply that competitors are audited individually (each is a domain subject to quota), but not beyond what the schema conveys. 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?

States a specific verb and resource ("Compare a website's AI visibility head-to-head against named competitors") and makes clear it is a multi-domain comparison, which separates it from single-site siblings like get_ai_visibility and get_benchmark. An agent can pick it without opening a 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?

Gives concrete user-intent triggers ("how do I stack up against X and Y", "who does ChatGPT recommend instead of me") and names an explicit alternative path: call get_sample_audit first for users without a Website Auditor subscription. It also tells the agent what happens when quota is insufficient versus exhausted, so the routing decision is fully specified.

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