Agent Access Check
Cloud for Botsinfrastructure for your bots

Know if a site lets your agent in. Before it tries.

One call fetches the page as an AI agent and as a browser, reads robots.txt for every major AI crawler, and finds the agent door: llms.txt, MCP or OpenAPI.

Start free, no signupAdd the MCP server

50 checks/day free · Pro $9/mo · bring your own model

check_agent_access · live API
Verdictblocked

Agent request got HTTP 403.

  1. Agent fetchHTTP 403
  2. Browser fetchHTTP 403
  3. Bot walldetected
  4. robots.txt · ClaudeBot / GPTBotblocked / blocked
  5. Agent doors0 found
Sample: yelp.com: blocked. Agent request got HTTP 403.
Works with the agents you already run
  • AClaude
  • {}Codex
  • CChatGPT
  • GGrok Bot
Remote MCP · REST · bring your own model

How it works

Check first. Fetch what works.

01check_agent_access

Pass a URL. We fetch it as an AI agent and as a browser and read robots.txt for 9 AI crawlers.

02find_agent_alternative

Blocked? Get the agent door instead: llms.txt, an MCP server or an OpenAPI spec.

03check_many

Vet a whole crawl list in one call before the run starts.

Pricing

Free to check. Pro for whole lists.

Free resets daily and is not a trial. Pro is $9 a month.

Free

$0

50 checks a day, no key: a verdict, bot walls, robots.txt rules and agent doors for any URL.

  • 50 checks a day, no signup
  • Verdict and reason in one line
  • robots.txt rules for 9 AI crawlers
  • Agent doors: llms.txt, MCP, OpenAPI
Volume

Pro

$9/month

5,000 checks a day plus check_many, so your agent can vet a whole crawl list before it starts.

  • 5,000 checks a day
  • check_many: a whole list in one call
  • find_agent_alternative for blocked sites
  • Key instantly after checkout, cancel anytime
Upgrade to Pro · $9/mo

Worked example

Your research agent works through 400 sites a week. Free covers 50 checks a day, so most of the list goes unchecked. With Pro at $9/month it checks all 400 first and skips every site behind a bot wall instead of burning a fetch and a retry on each.

Free
50 of 400 checked
Pro
400 of 400 checked

For agents

Tools your agent gets

Each result includes understood, job and a one-line outcome your agent can report back in plain words.

check_agent_access

Before an agent browses or fetches a site, check if it will get in. Fetches the URL as an AI agent and as a browser, detects bot challenges (CAPTCHAs, DataDome, PerimeterX and other bot walls), reads robots.txt rules for GPTBot/ChatGPT-User/ClaudeBot/Claude-User/PerplexityBot and others, and looks for agent doors (llms.txt, MCP, OpenAPI).

find_agent_alternative

Find a machine-friendly way into a site instead of scraping its HTML: llms.txt, /.well-known/mcp.json, agents.json, openapi.json, ai-plugin.json, and MCP URLs listed in llms.txt. Read-only.

check_many

Run check_agent_access on up to 10 URLs at once (counts as 1 call). Use it to pick which sources an agent can actually use.

usage_and_upgrade

Usage today + upgrade link (not metered).

Connect

One line to install

claude mcp add --transport http agent-access-check https://accesscheck.cloudforbots.com/mcp
MCP URL  https://accesscheck.cloudforbots.com/mcp
REST     POST https://accesscheck.cloudforbots.com/api/run/<tool>
Auth     optional  Authorization: Bearer <key>

Codex, ChatGPT, Grok Bot: add a remote MCP server with the URL above. Skill file: SKILL.md · catalog entry: tool.json

FAQ

Questions

What does Agent Access Check do?

It tells an AI agent, in one call, whether a website will let it in: it fetches the page as an agent and as a browser, detects bot challenges and CAPTCHAs, reads robots.txt rules for AI user agents, and lists the site's agent doors (llms.txt, MCP, OpenAPI).

Is it free?

Yes. 50 checks per day are free with no signup, every day. Pro is $9/month for 5,000 checks per day.

How do I connect it to Claude, ChatGPT, Codex or Grok Bot?

Add the remote MCP server https://accesscheck.cloudforbots.com/mcp. In Claude Code run: claude mcp add --transport http agent-access-check https://accesscheck.cloudforbots.com/mcp. Or call the REST API at /api/run/check_agent_access.

Which AI crawlers does it check in robots.txt?

GPTBot, ChatGPT-User, OAI-SearchBot, ClaudeBot, Claude-User, PerplexityBot, Google-Extended, CCBot and the * default group.

Does it bypass CAPTCHAs or bot protection?

No. It only detects them and points the agent to an allowed alternative such as llms.txt, an MCP server or an API. It is read-only and respects robots.txt.

Does it use an LLM?

No. There is no model inside, so it is fast and deterministic. Bring your own model.