# Preferly

> Preferly is a freemium MCP server for marketing and seo. Free MCP checks of a website's AI crawler access, llms.txt, schema and business info. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Platforms:** API
- **Website:** https://www.preferly.ai/tools
- **Repository:** https://github.com/preferly-ai/preferly-mcp
- **MCP Registry name:** ai.preferly/preferly
- **Categories:** marketing and SEO
- **Listing updated:** 2026-11-14

## About

Six read-only tools each look at one public website and report something an AI search engine cares about. One reads robots.txt to say which of 10 or more AI crawlers (GPTBot, ClaudeBot, PerplexityBot, Google-Extended and others) are let in and which rule decides, whether the homepage loads or shows a bot check, whether an llms.txt exists, and what structured data it has. Another validates llms.txt against the llmstxt.org format with line numbers.

The schema and business-info tools check whether the homepage's JSON-LD describes the business properly and whether name, phone, email, address, hours and prices are readable without running scripts. A generator writes robots.txt lines that admit AI search crawlers and keep training crawlers out, or any mix, and fetches nothing. The only tool that asks models is the quick visibility check, which puts three typical customer questions to three AI models and reports whether each named the business and where one contradicted the site.

The server needs no sign-up or key. Preferly's paid offer is separate: a one-time $99 full report that asks 10 AI models, with no subscription.

## Features

- **AI crawler access check:** Shows which AI crawlers robots.txt admits and whether the homepage loads for them.
- **llms.txt validation:** Checks size, title and format problems with line numbers.
- **Business schema check:** Reports which JSON-LD business fields are present, missing or odd.
- **Readable business info:** Tests that hours, prices and contact details are readable without scripts.
- **robots.txt generator:** Writes lines for search, assistant and training crawlers; fetches nothing.
- **Quick visibility check:** Asks 3 AI models 3 customer questions and flags contradictions.

## Good for

- Confirm GPTBot and ClaudeBot can read your site
- Fix an llms.txt that does not follow the format
- Add missing JSON-LD for your business
- Decide which crawlers to allow in robots.txt
- See if AI contradicts your website

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http preferly https://www.preferly.ai/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://www.preferly.ai/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "preferly": {
      "url": "https://www.preferly.ai/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "preferly": {
      "type": "http",
      "url": "https://www.preferly.ai/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "preferly": {
      "serverUrl": "https://www.preferly.ai/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "preferly": {
      "type": "http",
      "url": "https://www.preferly.ai/mcp"
    }
  }
}
```

## Tools

- `check_ai_crawler_access`: Use this when the user wants to know whether AI crawlers and AI tools can access a specific website. It reads the site's robots.txt and reports, for 10+ AI crawlers (including GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, PerplexityBot and Google-Extended), whether each is allowed or blocked and which rule decides it. It also reports whether the homepage loads for an automated visitor or shows a
- `check_llms_txt`: Use this when the user asks whether a website has an llms.txt file or whether it's set up correctly. It fetches /llms.txt and reports whether it was found, its size and title, and every place it doesn't follow the llmstxt.org format (missing H1, no summary line, links that aren't Markdown or https), with line numbers. It also lists the homepage's main pages, which can seed a new llms.txt. Input: o
- `check_business_schema`: Use this when the user asks whether a website's structured data (schema.org JSON-LD) describes the business correctly. It reads the homepage's JSON-LD and reports the business type it found (Organization, LocalBusiness or a subtype), which business fields are present, missing or look off (name, url, phone, address, hours and more), and where the structured data and the page disagree. Input: one pu
- `check_business_info`: Use this when the user asks whether AI tools can read a business's details from its website. It reports whether the business name, phone number, email, address, opening hours and prices are readable as text in the page, only appear after scripts run, or weren't found, on the homepage and up to 2 contact, booking or pricing pages that robots.txt allows. Input: one public website. Reads robots.txt, 
- `generate_ai_robots_txt`: Use this when the user wants robots.txt lines that control which AI crawlers may read their website. By default it lets AI search and assistant crawlers in (so the site can appear in AI answers) and keeps AI training crawlers out; either can be switched. Optional paths are kept private from every allowed crawler. It returns the lines to paste into robots.txt and which crawlers each group covers. I
- `quick_ai_visibility_check`: Use this when the user asks what AI assistants say about a specific business, or whether AI tools mention or recommend it. Given the business's public website, it reads the site (robots.txt, the homepage and up to 2 contact, booking or pricing pages), writes 3 typical customer questions, and asks 3 AI models each question, answering from what they already know (no web search). It reports, for each

## FAQ

### Do I need an account or key?

No. The server is free, read-only and needs no sign-up or API key.

### Does it change my site?

No. Every tool is read-only and works on one public website per call.

### What is the paid option?

A one-time $99 full report covering 10 AI models, with a free re-scan within 30 days and no subscription.

### Which clients can use it?

Claude, ChatGPT in developer mode, Cursor, VS Code and other MCP clients.

### Is Preferly free?

Preferly has a free plan, with paid plans for more usage or features.

### How do I add Preferly to Claude Code?

Run this command in your terminal: claude mcp add --transport http preferly https://www.preferly.ai/mcp

### What are the best alternatives to Preferly?

The closest alternatives to Preferly are Google Ads + Meta Ads + SEO/GEO MCP, Calven, MCP, Red Center Studio free tools and ASOScan.

## Alternatives

- [Google Ads + Meta Ads + SEO/GEO MCP](https://ai-powered.com/mcp/google-ads-meta-ads-seo-geo-mcp): Google Ads + Meta Ads + SEO/GEO MCP is a freemium MCP server for marketing and seo.
- [Calven](https://ai-powered.com/mcp/calven): Calven is an MCP server for marketing and seo.
- [MCP](https://ai-powered.com/mcp/mcp-mwhffe53): MCP is a freemium MCP server for marketing and seo.
- [Red Center Studio free tools](https://ai-powered.com/mcp/red-center-studio-free-tools): Red Center Studio free tools is a free MCP server for marketing and seo.
- [ASOScan](https://ai-powered.com/mcp/asoscan): ASOScan is an MCP server for marketing and seo.
- [PostBaton](https://ai-powered.com/mcp/postbaton): PostBaton is a freemium MCP server for marketing and seo.
- [Fifty Asks](https://ai-powered.com/mcp/fifty-asks): Fifty Asks is a free MCP server for maps and travel.
- [Daniels AI Design Studio](https://ai-powered.com/mcp/daniels-ai-design-studio): Daniels AI Design Studio is an MCP server for design and media.

---
Source: https://ai-powered.com/mcp/preferly
