# AI Visibility MCP Server (`steadfeed/ai-visibility-mcp`) Actor

Connect ChatGPT, Claude or Cursor and ask: can AI assistants find and understand my site? One-call AI visibility report with a 0-100 score and prioritized fixes: AI-crawler access, structured data, llms.txt, speed and accessibility.

- **URL**: https://apify.com/steadfeed/ai-visibility-mcp.md
- **Developed by:** [Steadfeed](https://apify.com/steadfeed) (community)
- **Categories:** MCP servers, SEO tools, AI
- **Features:** Limited permissions, Single-tenant, Server interface
- **Stats:** 1 total users, 0 monthly users, 0.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $10.00 / 1,000 ai visibility reports

This Actor is paid per event and usage. You are charged both the fixed price for specific events and for Apify platform usage.

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

## AI Visibility MCP Server

**Ask your AI assistant: "Can ChatGPT and other AI tools find and understand my website?"** Connect this server to ChatGPT, Claude, Cursor or any MCP client. One call returns a plain-English AI visibility report with a 0-100 readiness score and the fixes that matter most.

### What the report checks

| Check | What it tells you |
|---|---|
| AI crawler access | Whether ChatGPT search, Claude, Perplexity, Apple and Google crawlers may read your site (robots.txt, noindex, firewall signals) |
| Structured data and page basics | JSON-LD, title, description, canonical, Open Graph, llms.txt |
| Mobile speed | Google PageSpeed performance score and top fixes (included, no Google key needed) |
| Accessibility | WCAG A/AA problems in the static HTML |
| Tech stack | CMS, frameworks, analytics and CDN (context for the fixes) |
| Real AI answers (optional) | Whether ChatGPT / Perplexity actually name your brand, using your own AI key |

### Tools

| Tool | Use it for |
|---|---|
| `ai_visibility_report` | The one-call report for a site. Start here. |
| `audit_ai_crawler_access` | Detail on each AI crawler |
| `audit_schema_ai_readiness` | Detail on structured data per page |
| `check_ai_search_visibility` | Ask ChatGPT / Perplexity buyer questions and measure brand mentions (your own AI key) |
| `audit_pagespeed` | PageSpeed for many URLs (your free Google key) |
| `audit_accessibility` | WCAG checks for many URLs |
| `detect_tech_stack` | Tech stack for many sites |

### Connect it

**ChatGPT** (web, Developer mode on; full support on Business/Enterprise, read-only tools on Pro): open Plugins (or Settings → Apps & Connectors), choose **Add custom MCP server** / Create, and enter:

- Server URL: `https://mcp.apify.com?tools=steadfeed/ai-visibility-mcp`
- Authentication: **OAuth** (no client ID or secret needed)

Sign in to Apify when asked, then type `@` in a chat, pick the connector and ask: *"Give me an AI visibility report for example.com."*

**Claude** (claude.ai or Claude Desktop, any plan; Free allows one custom connector): Customize → Connectors → Add → Add custom connector. Name it "AI Visibility", URL `https://mcp.apify.com?tools=steadfeed/ai-visibility-mcp`, keep the detected sign-in settings, then sign in to Apify.

**Cursor** (Settings → MCP → Add new MCP server, or `~/.cursor/mcp.json`), **VS Code, Claude Code and other clients that accept headers** can connect directly with an Apify API token from [Console → Settings → API & Integrations](https://console.apify.com/settings/integrations):

```json
{ "mcpServers": { "ai-visibility": { "url": "https://steadfeed--ai-visibility-mcp.apify.actor/mcp", "headers": { "Authorization": "Bearer <your Apify API token>" } } } }
```

Or use OAuth instead of a token: `{ "mcpServers": { "ai-visibility": { "url": "https://mcp.apify.com?tools=steadfeed/ai-visibility-mcp" } } }`.

### Example prompts

- "Give me an AI visibility report for example.com and explain the top 3 fixes."
- "Check example.com plus /pricing and /about: can ChatGPT and Perplexity crawlers read them?"
- "Is our structured data good enough for AI search? Check these 3 pages."

Open source (MIT): [steadfeed-dev/steadfeed-site-audit-mcp](https://github.com/steadfeed-dev/steadfeed-site-audit-mcp). The broader [Site Audit MCP Server](https://apify.com/steadfeed/steadfeed-site-audit-mcp) adds page-change and pay-transparency tools.

You need a free Apify account. The free plan's monthly credit covers well over a hundred reports.

### Pricing

Pay per use, billed to your Apify account. No subscription.

| What | Price |
|---|---|
| Full AI visibility report | $0.01 for the report, plus the checks it runs (about $0.015 for a homepage), so about $0.025-0.03 all-in |
| Each single-purpose tool call | $0.001 plus the checked pages at the underlying tool's price ($0.002-$0.005 per page) |
| Real AI answers (optional) | $0.01 per analysed answer, plus your AI provider's own cost (about $0.0002-$0.002) |

### Good to know

- If fewer than 2 of the 4 core checks can run (for example, the site blocks automated checkers), the report is labeled "limited result" and the $0.01 report fee is not charged.
- Only public pages are checked. Nothing is stored beyond your own Apify run.
- Optional API keys (OpenAI, Perplexity, Google) are passed to Apify as secret input, used only for that call, and never returned.
- The report measures whether AI systems can reach and understand your site. It does not guarantee rankings or AI citations.

# Changelog

This Actor's version history is a separate document: https://apify.com/steadfeed/ai-visibility-mcp/changelog.md

# Actor input Schema

## Actor input object example

```json
{}
```

# Actor output Schema

## `server` (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 = {};

// Run the Actor and wait for it to finish
const run = await client.actor("steadfeed/ai-visibility-mcp").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 = {}

# Run the Actor and wait for it to finish
run = client.actor("steadfeed/ai-visibility-mcp").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 '{}' |
apify call steadfeed/ai-visibility-mcp --silent --output-dataset

```

## MCP server setup

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

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/DcIxIM7mEhqj4VH6k/builds/AjHWCZbgg8zsRzV7J/openapi.json
