Agent Access Check MCP server
com.botrecipe/accesscheckbotrecipe.comstreamable-httpv1.0.1Scanned
Check if a website will block your AI agent and find its llms.txt, MCP or OpenAPI door.
4 tools: 2 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 2
- Can send data out · 3
- 1 finding, 1 high
Tools listed without sign-in. Remote posture
With Anlyon
2 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Agent Access Check MCP server can do
The Agent Access Check MCP server is published by botrecipe.com, a domain the MCP Registry verified. It has 4 tools. It can create or change data (2 tools: check_agent_access and check_many), but cannot delete data. 2 tools only read.
2 tools bring in text other people can write (check_agent_access and find_agent_alternative); 3 tools can send data out of your system (check_agent_access, find_agent_alternative and check_many).
The fixed checks matched 1 finding, 1 of them high severity (sensitive-path). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 12, 2026, version 1.0.1.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
4 tools
Changes things 2Claude Code: ask
check_agent_accessBefore an agent browses or fetches a site, check if it will get in.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe description's first sentence says "browse": it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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). Returns verdict: open | challenged | blocked | robots_disallowed | unreachable, plus advice. Read-only. Use it before an automated web task, not for pages you already fetched successfully.
check_manyRun check_agent_access on up to 10 URLs at once (counts as 1 call).Can send data outNo findings
Why it is in this group
- The description's first verb is "run": a word for a change.
What it can reach
- outboundThe input takes a URL (input.urls): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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.
Only reads 2Show 2 read-only tools
find_agent_alternativeFind 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.Reads text others writeCan send data out1 finding
Why it is in this group
- The name "find_agent_alternative" says "find": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "find" and "html": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Findings
- High
The description refers to "/.well-known/mcp.json".
What this check looks forMatched text
description: "...instead of scraping its HTML: llms.txt, /.well-known/mcp.json, agents.json, openapi.json, ai-plugin.j..."
Description, as the server wrote it 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.
usage_and_upgradeShow today's usage for your key or IP and the $9/month upgrade link.No findings
Why it is in this group
- The description's first verb is "show": a word for reading.
Description, as the server wrote it Show today's usage for your key or IP and the $9/month upgrade link. Free tier: 50 calls/day. Not metered.
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out3
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:35 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 2
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://accesscheck.cloudforbots.com/mcp: tools/list returned 4 tools to an anonymous client, including check_agent_access (write), check_many (write)
Findings
Matches of fixed checks, with the text they matched.
The description refers to "/.well-known/mcp.json".
What this check looks forMatched text
description: "...instead of scraping its HTML: llms.txt, /.well-known/mcp.json, agents.json, openapi.json, ai-plugin.j..."
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http accesscheck https://accesscheck.cloudforbots.com/mcpclaude mcp add --transport http accesscheck https://accesscheck.cloudforbots.com/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__accesscheck__usage_and_upgrade"
],
"ask": [
"mcp__accesscheck__check_agent_access",
"mcp__accesscheck__find_agent_alternative",
"mcp__accesscheck__check_many"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as accesscheck. Review it before you use it.
Capability tags behind 3 rules
- mcp__accesscheck__check_agent_access untrusted-input, outbound
- mcp__accesscheck__find_agent_alternative untrusted-input, outbound
- mcp__accesscheck__check_many outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.botrecipe/accesscheck/verify?hash=3caa3071bb2f672ef572f47166092e119112fd0d2f59279b3add16572b49af70" | jq -e '.changed == false'Pinned hash 3caa3071bb2f, from Nov 12, 2026, 18:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.botrecipe/accesscheck/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.botrecipe/accesscheck)Source: MCP Registry. Synced Oct 21, 2026, 17:52 UTC.
Agent Access Check MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Agent Access Check MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 2 of which can change, send or delete something, and 1 finding (1 high) from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Agent Access Check MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Agent Access Check MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Agent Access Check MCP server have?
- 4 tools: 2 write, 2 read. check_agent_access, check_many, find_agent_alternative and usage_and_upgrade.
Does the Agent Access Check MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Agent Access Check MCP server send data to outside services?
- 3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): check_agent_access, find_agent_alternative and check_many.
Has the Agent Access Check MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 12, 2026.