llms.txt Checker - AI Readiness Audit

io.github.apifymcpfactory-droidPublished by GitHub account apifymcpfactory-droidv1.0.0Updated Oct 24, 2026

Checks llms.txt, AI crawler access in robots.txt, and sitemap - with a 0-100 AI readiness score.

The publisher's own server: audit.domains - Domain Valuation

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingDeveloper Tools

Overview

AI-generated overview

A hosted Apify MCP tool that audits a website's AI readiness: llms.txt, AI crawler rules in robots.txt, sitemap, and a 0–100 score.

What you can do
Audit a website's AI readiness in one pass: check for llms.txt and llms-full.txt, inspect robots.txt policy for AI crawlers such as GPTBot, ClaudeBot, PerplexityBot, Google-Extended, CCBot and Bytespider, and check sitemap.xml. Return a 0–100 AI readiness score with a plain-English list of what to fix. Run checks in bulk, with one output row per input site.
When to use it
Useful when you want an assistant to assess whether a site is discoverable and usable by AI crawlers and assistants, or to produce a prioritized fix list for llms.txt, robots.txt and sitemap setup across many sites.
Requirements
Remote hosted endpoint at mcp.apify.com; no installation. An Apify account and API token sent as an Authorization Bearer header, or OAuth if the MCP client supports it. Usage is billed to the Apify account.
Before you install
Paid pay-per-use tool: a flat fee per run plus a flat fee per result, charged to the Apify account tied to the token. The Authorization header carries an Apify API token, so keep it secret. The tool fetches the target sites' public files, so those URLs are sent to Apify.

Installation

In SourceWeft

  1. Open llms.txt Checker - AI Readiness Audit in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.apifymcpfactory-droid%2Fllms-txt-checker/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "llms-txt-checker-ai-readiness-audit": {
      "type": "http",
      "url": "https://mcp.apify.com/?tools=apifmcpfactory/llms-txt-checker"
    }
  }
}

README

MCP Factory: pay-per-use MCP tools for AI agents

MCP Factory builds small, reliable, pay-per-use tools that AI agents can call over the Model Context Protocol (MCP). Each tool runs as an Apify Actor and is exposed through Apify's hosted MCP server — no installation, no infrastructure, no subscription. Your agent calls the tool directly; usage bills through your Apify account at flat, transparent per-result prices.

The tools

🔍 Tech Stack Detector

Find out what any website is built with. Scans a list of URLs and identifies the technologies behind each site — CMS, ecommerce platform, web frameworks, analytics, CDN, web server, and more — using the open-source webappanalyzer fingerprint dataset (7,500+ technologies across 109 categories). A fast, affordable Wappalyzer / BuiltWith alternative at roughly $5 per 1,000 sites.

🧾 EU VAT Validator

Validate EU VAT numbers in bulk against VIES, the European Commission's official VAT validation service — and get the official consultation number on every check as audit evidence for tax inspections. Bulk-safe with automatic retries, tolerant of messy input formats, $5 per 1,000 validations flat.

🤖 llms.txt Checker

A complete AI readiness audit for any website in one pass: checks llms.txt, llms-full.txt, robots.txt AI-crawler policy (GPTBot, ClaudeBot, PerplexityBot, Google-Extended, CCBot, Bytespider), and sitemap.xml, then returns a 0–100 AI readiness score with a plain-English list of exactly what to fix. ~$5 per 1,000 sites.

Connect all three tools at once

One MCP server URL exposes any combination of tools. To give your agent the full MCP Factory toolkit:

https://mcp.apify.com?tools=apifmcpfactory/tech-stack-detector,apifmcpfactory/eu-vat-validator,apifmcpfactory/llms-txt-checker

Claude Desktop (claude_desktop_config.json):

json
{    "mcpServers": {        "mcp-factory": {            "command": "npx",            "args": [                "mcp-remote",                "https://mcp.apify.com?tools=apifmcpfactory/tech-stack-detector,apifmcpfactory/eu-vat-validator,apifmcpfactory/llms-txt-checker",                "--header",                "Authorization: Bearer YOUR_APIFY_TOKEN"            ]        }    }}

Cursor (.cursor/mcp.json):

json
{    "mcpServers": {        "mcp-factory": {            "url": "https://mcp.apify.com?tools=apifmcpfactory/tech-stack-detector,apifmcpfactory/eu-vat-validator,apifmcpfactory/llms-txt-checker",            "headers": {                "Authorization": "Bearer YOUR_APIFY_TOKEN"            }        }    }}

Replace YOUR_APIFY_TOKEN with your API token from Apify Console. New Apify accounts include free monthly usage credit, so you can try every tool before paying anything.

How pricing works

Every tool is pay-per-event: a small flat fee per run plus a flat fee per result. No subscriptions, no tiers, no minimums. Usage is billed through the Apify account whose token your agent uses — you can see every run, result, and charge in Apify Console.

About

MCP Factory publishes on the Apify platform as apifmcpfactory. Each tool is designed around the same principles: one clear job, bulk-safe execution (one output row per input, always), honest pricing, and output an AI agent can use without post-processing.

Source: README.md at commit b6e0848

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.

Other Audit integrations