# Local AI Presence Audit — GBP, Reviews & AI Readiness (`travelmonitorlab/local-ai-presence-audit`) Actor

Full local presence audit in one run: Google Business Profile data, recent reviews (urgency-classified, owner-response check), website AI-readiness scan (ChatGPT/Perplexity), presence score /100, ready-to-use llms.txt + JSON-LD + action plan. API + MCP ready, x402/USDC payable.

- **URL**: https://apify.com/travelmonitorlab/local-ai-presence-audit.md
- **Developed by:** [Travel Monitor Lab](https://apify.com/travelmonitorlab) (community)
- **Categories:** Marketing, AI, SEO tools
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

Pay per event

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## Local AI Presence Audit — GBP, Reviews & AI Readiness

**Audit any local business in a single run**: Google Business Profile data, recent reviews with urgency classification and owner-response detection, website AI-readiness scan (ChatGPT, Perplexity, Gemini, Google AI Overviews), a transparent **presence score /100**, and **ready-to-use deliverables** — a publishable `llms.txt`, a prefilled `LocalBusiness` JSON-LD snippet, AI-drafted responses to negative reviews, and a prioritized action plan.

### Use this tool when...

- You need to **audit a local business's online presence** (restaurant, hotel, salon, shop, craftsman) before selling it marketing services.
- You want to know **whether ChatGPT, Perplexity or Gemini can "see" a business** — its website structured data, `llms.txt`, and `robots.txt` AI-crawler rules, plus its Google Business Profile strength (the #1 source LLMs use for local answers).
- You need **review intelligence**: latest Google reviews, urgency classification (critical = hygiene/safety accusations via a from-scratch multinomial Naive Bayes classifier), and which negative reviews still have no owner response.
- You want **deliverables, not just data**: every run generates a ready-to-publish `llms.txt`, a ready-to-paste `LocalBusiness` JSON-LD block (with real aggregateRating when found), suggested public responses to unanswered negative reviews, and a prioritized action plan.
- You are an **AI agent** and need a payable, structured audit tool: this actor is API + MCP ready and supports **x402 agentic payments (USDC on Base)**.

### Features

- **Google Maps audit** — resolves the business from a simple query (`name + city`), extracts name, category, global rating, review count, address, phone, website.
- **Review analysis** — scrapes the most recent reviews (1–30), classifies urgency with a Naive Bayes model (FR/EN corpus, confidence score, abstention below threshold), detects owner responses.
- **Website AEO/GEO scan** — 7-criterion Answer Engine Optimization audit, no browser cost: JSON-LD presence, LocalBusiness schema, meta description, H1, Open Graph, `/llms.txt`, and `robots.txt` rules for AI crawlers (GPTBot, ClaudeBot, PerplexityBot, Google-Extended, CCBot, anthropic-ai), plus FAQ schema detection.
- **Presence score /100** — transparent breakdown: website AI-readiness (40 pts), Google profile strength (35 pts), review health (25 pts).
- **Auto-generated deliverables** — `llms.txt`, LocalBusiness JSON-LD, review response drafts (French templates), prioritized action plan. Stored in the key-value store (`SUMMARY`, `LLMS_TXT`, `JSONLD`) and in the dataset.
- **Never fails silently** — invalid input, rate-limits or markup changes produce a structured dataset item (`verdict: input-error | error | partial | demo-empty`) with a `howToFix` hint. Agents can rely on the output contract.
- **Dry-run mode** — set `dryRun: true` to test the full pipeline without any billing event.

### Input

| Field | Type | Description |
|---|---|---|
| `query` | string | Business name + city for Google Maps resolution (e.g. `Boulangerie Paul Mersch`). Optional. |
| `websiteUrl` | string | Business website to scan for AI-readiness. Optional. |
| `maxReviews` | integer | Reviews to analyze, 1–30 (default 15). |
| `language` | string | Google Maps UI language (default `fr`). |
| `dryRun` | boolean | Skip all charges (default false). |
| `proxyConfiguration` | object | Defaults to Apify RESIDENTIAL (required — Google blocks datacenter IPs). |

At least one of `query` / `websiteUrl` is recommended. With neither, a small demo audit runs instead of failing.

### Output

One dataset item per audit:

- `verdict`: `ok` (both sources), `partial` (one source), `error` / `demo-empty` (structured failure, never a crashed run)
- `business`, `auditedAt`, `presenceScore` (`total`, `website_ai`, `google_profile`, `review_health`)
- `websiteAudit`: full AEO detail per criterion
- `googleProfile`: name, category, rating, reviewCount, address, phone, website
- `reviews[]`: author, rating, text, date, `ownerResponse`, `urgency`, `urgencyConfidence`
- `actionPlan[]`: prioritized fixes (critical reviews first)
- `deliverables`: `llms_txt`, `jsonld_localbusiness`, `review_responses[]`

Key-value store records: `SUMMARY` (executive digest), `LLMS_TXT`, `JSONLD`.

### Pricing (pay-per-event)

| Event | Price | When |
|---|---|---|
| `run-started` | $1.00 | Once per run (covers residential proxy + browser cost) |
| `business-audited` | $0.50 | One business fully audited and scored |

Compute units are paid by you as the caller; `dryRun: true` skips all events for free testing.

### x402 agentic payments

This actor is eligible for **x402 agentic payments** — AI agents can call it without an Apify account and pay per use in **USDC on Base** (HTTP 402 challenge, `X-APIFY-PAYMENT-PROTOCOL: X402` header). Fully machine-payable, no signup required.

### FAQ

**Why does the audit need residential proxies?** Google Maps blocks datacenter IPs. The default proxy configuration handles it — don't override it unless you know why.

**Is the presence score comparable between businesses?** Yes — the rubric is fixed (40/35/25). It is designed for prospecting benchmarks ("your competitors score 70, you score 35").

**Can I run it on a schedule?** Yes — schedule weekly/monthly runs to track score evolution. Combine with the `review-radar` actor for continuous new-review alerts.

**What if my business has no website?** Run with `query` only — you still get the Google profile + reviews audit, and the action plan will flag website creation as a priority.

### Related actors by travelmonitorlab

- **review-radar** — continuous Google review monitoring with Slack alerts
- **aeo-ai-visibility-checker** — free website AI-visibility scan + llms.txt generator
- **Google Maps Business Scraper** — bulk lead extraction

***

*Built and maintained by [Adaga solutions](https://adagasolutions.lu) — Luxembourg. Managed presence service (we do all of this for you, monthly): [adagasolutions.lu/presence](https://adagasolutions.lu/presence/).*

# Actor input Schema

## `query` (type: `string`):

Business name + city used to find its Google Maps profile (e.g. 'Boulangerie Paul Mersch' or 'restaurant Esch-sur-Alzette'). The first, most relevant place is audited. Optional if websiteUrl alone is enough for you.

## `websiteUrl` (type: `string`):

Full URL of the business website (e.g. https://example.lu). Scanned without a browser for AI-readiness: JSON-LD structured data, LocalBusiness schema, meta description, H1, Open Graph, /llms.txt, and robots.txt rules for AI crawlers (GPTBot, ClaudeBot, PerplexityBot, Google-Extended, CCBot).

## `maxReviews` (type: `integer`):

Number of most recent Google reviews to scrape and classify (urgency detection, owner-response check). Between 1 and 30.

## `language` (type: `string`):

Google Maps interface language code (fr, en, de...). Affects localized labels parsing.

## `dryRun` (type: `boolean`):

When true, the actor runs fully but skips all pay-per-event charges. Use it for testing and integration QA.

## `proxyConfiguration` (type: `object`):

Apify proxy settings. Residential proxies are strongly recommended — Google Maps blocks datacenter IPs. Defaults to RESIDENTIAL.

## Actor input object example

```json
{
  "query": "restaurant Esch-sur-Alzette",
  "websiteUrl": "https://adagasolutions.lu",
  "maxReviews": 5,
  "language": "fr",
  "dryRun": true,
  "proxyConfiguration": {
    "useApifyProxy": true,
    "apifyProxyGroups": [
      "RESIDENTIAL"
    ]
  }
}
```

# Actor output Schema

## `auditReport` (type: `string`):

No description

## `summary` (type: `string`):

No description

## `llmsTxt` (type: `string`):

No description

## `jsonld` (type: `string`):

No description

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "query": "restaurant Esch-sur-Alzette",
    "websiteUrl": "https://adagasolutions.lu",
    "maxReviews": 5,
    "dryRun": true,
    "proxyConfiguration": {
        "useApifyProxy": true,
        "apifyProxyGroups": [
            "RESIDENTIAL"
        ]
    }
};

// Run the Actor and wait for it to finish
const run = await client.actor("travelmonitorlab/local-ai-presence-audit").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {
    "query": "restaurant Esch-sur-Alzette",
    "websiteUrl": "https://adagasolutions.lu",
    "maxReviews": 5,
    "dryRun": True,
    "proxyConfiguration": {
        "useApifyProxy": True,
        "apifyProxyGroups": ["RESIDENTIAL"],
    },
}

# Run the Actor and wait for it to finish
run = client.actor("travelmonitorlab/local-ai-presence-audit").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "query": "restaurant Esch-sur-Alzette",
  "websiteUrl": "https://adagasolutions.lu",
  "maxReviews": 5,
  "dryRun": true,
  "proxyConfiguration": {
    "useApifyProxy": true,
    "apifyProxyGroups": [
      "RESIDENTIAL"
    ]
  }
}' |
apify call travelmonitorlab/local-ai-presence-audit --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,travelmonitorlab/local-ai-presence-audit"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/PWDmdTTOk406blEqN/builds/CdIXN4lWD7StTyS1t/openapi.json