# GEO & AI Agent Readiness Audit (`bakos_bence/geo-agent-readiness-audit`) Actor

Bulk-audit public websites for Generative Engine Optimization (GEO) and AI agent readiness. Scores crawler access, schema, llms.txt, and agent discovery; keep / change / missing report per site. Unofficial public-page audit.

- **URL**: https://apify.com/bakos\_bence/geo-agent-readiness-audit.md
- **Developed by:** [Bakos Bence](https://apify.com/bakos_bence) (community)
- **Categories:** MCP servers, SEO tools, Agents
- **Stats:** 1 total users, 0 monthly users, 0.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $1,590.00 / 1,000 website auditeds

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.
Since this Actor supports Apify Store discounts, the price gets lower the higher subscription plan you have.

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

## What's an Apify Actor?

Actors are web data automations that power AI and operations. They run on the Apify platform to scrape websites, process data, connect APIs, and automate workflows.
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.
Actors are written with capital "A".

## 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.
The best way to integrate Actors is as follows.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — the [REST API](https://docs.apify.com/api/v2.md).

For usage examples, see the [API](#api) section below.

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).

# README

### What does GEO & AI Agent Readiness Audit do?

**Audit public websites** for **Generative Engine Optimization (GEO)** and **AI agent readiness** — scores, structured checks, and a prioritized **keep / change / missing** report per site. Bulk URL lists supported (up to 50 sites per run).

**Unofficial.** This Actor is **not affiliated with, endorsed by, or maintained by** OpenAI, Google, Anthropic, or the websites you submit (unless you operate them). It probes **public** pages only.

**Dashboards:** connect **Power BI**, **Tableau**, **Looker Studio**, or **Qlik** to the dataset API — see *Export to Power BI, Tableau, Looker Studio & Qlik* near the end. **AI agents:** paste this Actor’s Store page URL into an Apify-capable agent (MCP / Claude / Cursor with Apify), create an Apify account and API token once, and the agent can run the Actor and wire up the output.

Premium technical audit for teams preparing sites for AI search, coding agents, and MCP discovery — not a commodity scraper.

**Ecommerce GEO:** after auditing your storefront, monitor product facts with [Shopify Products Scraper](https://apify.com/bakos_bence/shopify-products-scraper) or [LEGO.com Product Scraper](https://apify.com/bakos_bence/lego-products).

#### What you get

- **GEO score** — AI search/retrieval crawler access, extractable HTML, schema, citability shape
- **Agent score** — `llms.txt`, markdown discovery, `.well-known` agent surfaces (MCP, API catalog, …)
- **Report** — good as-is / needs change / missing / priority actions (deterministic checks + LLM narrative)
- **Dataset row** per site + **Key-value `REPORT.md`** (and `REPORT-N.md` when bulk)

Checks are deterministic HTTP probes; the written report uses Apify's OpenRouter gateway when available.

#### How to run an audit

1. Open this Actor in [Apify Console](https://console.apify.com/).
2. Paste one or more public URLs in `websiteUrls`.
3. Start the run; read scores in the dataset and the full narrative in KV store `REPORT.md`.

**Single site:**

```json
{ "websiteUrl": "https://example.com" }
```

**Bulk:**

```json
{ "websiteUrls": ["https://example.com", "https://another.example"] }
```

Max **50** sites per run. One dataset row + one **Website audited** charge per successful site.

#### How much does it cost?

**Pay per event:** **$2.49 per website audited** on Free (lower on paid plans — see Pricing tab). Actor start is a small one-time fee per run. Platform compute is included.

This is **premium per-audit pricing** — priced for quality audits, not per-row commodity scraping.

#### Input

| Field | Description |
|-------|-------------|
| `websiteUrls` | List of public URLs to audit (preferred) |
| `websiteUrl` | Single-site alias (still works) |

#### Sample output fields

`websiteUrl`, `origin`, `geoScore`, `agentScore`, `gradeGeo`, `gradeAgent`, `checks`, `narrative`, `priority`, `fetchedAt`

```json
{
  "websiteUrl": "https://example.com",
  "origin": "https://example.com",
  "geoScore": 72,
  "agentScore": 55,
  "gradeGeo": "B",
  "gradeAgent": "C",
  "priority": [],
  "fetchedAt": "2026-08-27T12:00:00+00:00"
}
```

Full markdown report saved to key-value store as `REPORT.md`.

#### FAQ

##### Is this priced per 1,000 results?

No — primary billing is **per website audited** ($2.49 on Free). One charge per successfully audited site.

##### Does `llms.txt` guarantee AI Overview citations?

No tool guarantees citations. This audit scores discoverability and agent-friendly surfaces so you know what to fix.

##### Can AI agents call this via MCP?

Optional MCP server path (`/mcp`) with tool `audit_website(website_url)` when Standby is enabled.

##### Public pages only?

Yes — audit sites you own or are authorized to test. Unofficial; not affiliated with the platforms whose crawlers we score.

##### Something broke?

Open the **Issues** tab on this Actor’s page.

#### Related Actors

| Actor | Use together when… |
|-------|-------------------|
| [Shopify Products Scraper](https://apify.com/bakos_bence/shopify-products-scraper) | You fix GEO gaps then monitor **product catalog** freshness |
| [LEGO.com Product Scraper](https://apify.com/bakos_bence/lego-products) | You audit a brand site and track **official product MSRP** |
| [GEO & AI Agent Readiness Audit](https://apify.com/bakos_bence/geo-agent-readiness-audit) | *(this Actor)* — GEO + agent readiness scores and reports |

Profile: [bakos\_bence on Apify](https://apify.com/bakos_bence).

#### For AI agents & LLM apps

Paste this Actor’s **Apify Store URL** into an agent that can use Apify (MCP, Claude, Cursor, etc.). With an Apify account and API token, the agent can set input, run the Actor, and fetch the dataset.

**Actor ID:** `bakos_bence/geo-agent-readiness-audit`

**Purpose:** Audit public websites for GEO (AI search visibility) and AI agent readiness.

**Minimal input:**

```json
{ "websiteUrls": ["https://example.com"] }
```

**Output:** one dataset row per site with scores and checks; full narrative in KV `REPORT.md`.

**Pricing unit:** Website audited — **$2.49/audit** on Free.

#### Export to Power BI, Tableau, Looker Studio & Qlik

After a run, rows live in an Apify **dataset**. You can download JSON/CSV/Excel from the Dataset tab, or point BI tools at a **CSV URL** that refreshes when you scrape again.

**Prefer the token in the URL** (`token=`) — most tools only need “open this link as CSV”, with no custom headers.

##### Build a refreshable CSV URL

1. In Apify Console, open **Settings → Integrations** and copy an API token.
2. Save this Actor as a **Task** (optional but best for dashboards), run or **schedule** it once so there is a successful run.
3. Use the **latest successful task run** URL (replace `TASK_ID` and `YOUR_TOKEN`):

```text
https://api.apify.com/v2/actor-tasks/TASK_ID/runs/last/dataset/items?format=csv&clean=true&status=SUCCEEDED&token=YOUR_TOKEN
```

Or, from any finished run, open the **Dataset** tab, copy the dataset ID, and use:

```text
https://api.apify.com/v2/datasets/DATASET_ID/items?format=csv&clean=true&token=YOUR_TOKEN
```

Anyone with that URL can read the data — treat it like a password. For recurring dashboards, prefer the `actor-tasks/…/runs/last/…` form so refresh always hits the newest successful scrape.

##### Power BI

1. Open Power BI Desktop → **Home** → **Get data** → **Web**.
2. Paste the CSV URL (including `token=`).
3. When asked how to sign in, choose **Anonymous** → **Connect**.
4. Confirm the preview is a table (CSV). **Load** or **Transform data** as needed.
5. Publish / schedule refresh in the Power BI service using the same URL (task `runs/last` keeps it current after each scrape).

`401`: token missing/wrong, or you did not pick **Anonymous**.

##### Tableau

1. Install Tableau’s **REST API** connector from Tableau Exchange (Desktop **2023.3+**).
2. **Connect** → **To a Server** → **REST API**.
3. Paste the CSV URL (including `token=`). Set response format to **CSV**.
4. If the connector asks for auth and the token is already in the URL, leave credentials empty / anonymous; otherwise paste the same token as a Bearer access token.
5. Create an **extract**. Refresh the extract after scheduled Task runs (or point at `runs/last` so each refresh loads the latest success).

Plain **Text file** connect still works if you download CSV from the Dataset tab once — use REST when you want repeatable refresh.

##### Looker Studio

Looker Studio has no strong built-in “private CSV API” connector. Use Google Sheets as the bridge:

1. Create a Google Sheet. In **A1** enter:

```text
=IMPORTDATA("https://api.apify.com/v2/actor-tasks/TASK_ID/runs/last/dataset/items?format=csv&clean=true&status=SUCCEEDED&token=YOUR_TOKEN")
```

2. Wait until columns fill (Sheets refreshes IMPORTDATA periodically).
3. In Looker Studio → **Create** → **Report** → **Google Sheets** → select that spreadsheet / tab.
4. Build the report. After each Actor/Task run, refresh the Sheet (or wait for IMPORTDATA) then refresh the Looker data source.

One-off alternative: Dataset tab → download CSV → Looker Studio **File upload**.

##### Qlik

**REST connector** (refreshable):

1. In Qlik Cloud / Qlik Sense → **Add data** → **REST** (or create a REST connection in the Data load editor).
2. URL = the CSV URL including `token=`. Method **GET**.
3. Set the expected response type to **CSV** (or use `format=json` and JSON mode).
4. **Test connection**, pick the table, **Add** / **Load**.
5. **Reload** the app after scheduled scrapes; with `runs/last`, each reload pulls the latest successful dataset.

**Files:** Dataset tab → download CSV → **Add data** → upload the file (fine for a single snapshot).

#### SEO keywords

geo audit, ai agent readiness, llms.txt checker, generative engine optimization, website ai audit, schema markup audit, mcp discovery audit, apify geo audit

# Actor input Schema

## `websiteUrls` (type: `array`):

Paste one or more public homepage URLs to audit (max 50 per run).

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

Optionally paste a single URL (merged with the list above).

## Actor input object example

```json
{
  "websiteUrls": [
    "https://example.com"
  ]
}
```

# Actor output Schema

## `overview` (type: `string`):

Default dataset items.

## `reportMarkdown` (type: `string`):

Full narrative report.

# 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 = {
    "websiteUrls": [
        "https://example.com"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("bakos_bence/geo-agent-readiness-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 = { "websiteUrls": ["https://example.com"] }

# Run the Actor and wait for it to finish
run = client.actor("bakos_bence/geo-agent-readiness-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 '{
  "websiteUrls": [
    "https://example.com"
  ]
}' |
apify call bakos_bence/geo-agent-readiness-audit --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,bakos_bence/geo-agent-readiness-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/oFi7dMxj3hmHmOwKb/builds/8et2N9RHd6FpaMzBA/openapi.json