ai-visibility-check

Check AI Visibility

check_ai_visibility

Read-only

Check whether a business is visible to AI answer engines. Runs each query through a live AI search (Perplexity) and reports whether the business's site is cited, at what rank, and who gets cited instead. Pass 1-5 realistic customer-intent questions — what a potential customer would actually ask an AI (e.g. "best kitchen remodeler in Clearwater FL"). Never include the business's own name in a query. Returns a 0-100 visibility score, a tier, per-query results, the competing sources AI cited, and a shareable branded scorecard link.

Input Schema

TableJSON Schema

Name	Required	Description
`email`	No	Optional. Justin also offers a free human-run deep-dive fix report (wider query set, drafted the minute they ask, reviewed by Justin, delivered same day). If the user says they want it, ask for their email and pass it here. Only pass an email the user explicitly provided — never invent or reuse one.
`domain`	Yes	Business website domain, e.g. acme-plumbing.com
`queries`	Yes	1-5 customer-intent questions to test (without the business name)
`business_name`	No	Business name as customers say it (improves mention detection)

Output Schema

TableJSON Schema

Name	Required	Description
`tier`	Yes	Plain-language band for the score.
`score`	Yes	0-100 visibility score: the share of checked queries where the business was cited.
`results`	Yes	Per-query outcome, in the order the queries were checked.
`queries_cited`	Yes	Queries where the business was cited or named.
`scorecard_url`	Yes	Shareable branded scorecard page for this result.
`queries_checked`	Yes	Queries that completed (errored queries are excluded from scoring).

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already carry readOnlyHint=true, openWorldHint=true, and destructiveHint=false. The description meaningfully adds that the tool performs a live AI search via Perplexity, reports competitor sources, and produces a shareable scorecard link—useful behavioral and side-effect context beyond the annotations.

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?

The description is front-loaded with purpose, moves through inputs, usage notes, and outputs in dense but efficient language. Every sentence contributes actionable information, and the most important query guidance is highlighted.

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?

For a tool with 4 parameters, a complete output schema, and no sibling ambiguity, the description covers the workflow end-to-end: what the tool does, how to call it effectively, and what it returns. The optional email/fix-report parameter is already fully explained in the schema.

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%, so each parameter is already documented. The description reinforces the query-format guidance (1-5 realistic questions, no business name), but doesn't need to add semantics beyond what the schema already covers.

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 description uses a clear, specific verb and resource: 'Check whether a business is visible to AI answer engines.' It details the method (live Perplexity search), the reported outputs (citation, rank, competing sources), and distinguishes the result from a generic visibility check.

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

Usage Guidelines4/5

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

The description gives strong operational guidance: pass 1-5 realistic customer-intent questions and never include the business's own name. It clearly implies when to use the tool, though it does not explicitly state 'when not to use it' — but there are no sibling tools to disambiguate against.

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

All ai-visibility-check tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0

Disambiguation5/5

There is only one tool, so there are no overlapping purposes or ambiguities. The check_ai_visibility tool clearly maps to a single, distinct action for the server.

Naming Consistency5/5

The sole tool uses a clean verb_noun snake_case pattern that matches the server name. With only one tool, there is no naming mix or deviation.

Tool Count4/5

One tool is slightly on the low side for an MCP server, but the server's stated purpose is deliberately narrow: performing an AI visibility check. It feels mildly under the typical multi-tool scope yet remains reasonable for such a focused operation.

Completeness4/5

The tool fully covers the main outcome of the domain by scoring AI visibility, showing per-query citations, identifying competitors, and generating a scorecard link. Minor gaps such as retrieving historical checks or managing previous reports are absent, but they are not essential to the core single-purpose workflow.

Resources

Need Help?