Skip to content

AISeeWhy MCP server

com.aiseewhy/aiseewhyaiseewhy.comstreamable-httpv1.2.0Scanned

Can ChatGPT, Claude and Perplexity crawlers read your page? Audit, fixes, compare, monitoring.

9 tools: 4 change things and 5 only read.

Tools: 0 delete, 0 irreversible, 4 write, 5 read.
  • Reads private data · 1
  • Reads text others write · 9
  • Can send data out · 6
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

4 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.
Govern this server →

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 AISeeWhy MCP server can do

The AISeeWhy MCP server is published by aiseewhy.com, a domain the MCP Registry verified. It has 9 tools. It can create or change data (4 tools: audit_url, audit_sitemap, crawl_site and watch_site), but cannot delete data. 5 tools only read.

1 tool reads private data (show_ai_crawler_check); 9 tools bring in text other people can write (show_ai_crawler_check, audit_url, audit_sitemap and 6 more); 6 tools can send data out of your system (show_ai_crawler_check, audit_url, compare_urls and 3 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.

Last scanned Nov 21, 2026, version 1.2.0.

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.

9 tools

Changes things 4Claude Code: ask
  • audit_sitemapAudit up to 10 pages listed in a sitemap or sitemap index.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Audit up to 10 pages listed in a sitemap or sitemap index. Returns one summary line per page plus the full report of every page with findings. Needs an API key.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
    • title: Audit pages from a sitemap
  • audit_urlAudit one URL: fetch it as 16 AI and search crawlers plus curl and a browser, check robots.txt, structured data, answer-first content, freshness, hreflang and llms.txt, plus classi…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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • 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
    Audit one URL: fetch it as 16 AI and search crawlers plus curl and a browser, check robots.txt, structured data, answer-first content, freshness, hreflang and llms.txt, plus classic on-page SEO (title, meta description, H1, canonical, noindex, image alt text, broken links). Returns a Markdown report with findings and fixes. language: report language code (en, de, ja, …).

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
    • title: Audit a URL for AI crawlers
  • crawl_siteSEO site audit: crawl up to 50 pages (up to 90 seconds) of a site from a start page by following internal links (then the sitemap), as a browser and respecting robots.txt.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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe name "crawl_site" says "crawl": it reads web pages, which anyone can write.
    • untrusted-inputThe description's first sentence says "crawl": 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
    SEO site audit: crawl up to 50 pages (up to 90 seconds) of a site from a start page by following internal links (then the sitemap), as a browser and respecting robots.txt. Reports broken and redirected internal links, duplicate titles and descriptions, orphan, deep and thin pages, sitemap entries that are noindex, redirect or name another canonical, and on-page SEO problems counted across pages. Needs an API key.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
    • title: Crawl a site for SEO
  • watch_siteAdd a URL to the account's scheduled monitoring (freq: daily or weekly).Reads text others writeCan send data outNo findings

    Why it is in this group

    • The description's first verb is "add": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • 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
    Add a URL to the account's scheduled monitoring (freq: daily or weekly). The owner gets an email when a check finds a new P1 problem or the score drops by 10 or more. Needs an API key; adding the same URL again only changes the frequency.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: false
    • title: Monitor a URL
Only reads 5Show 5 read-only tools
  • compare_urlsAudit 2 or 3 URLs (yours and competitors') and compare them side by side: score, P1/P2/P3 counts, blocked crawlers, llms.txt, structured data, text without JavaScript.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "compare_urls" says "compare": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe name "compare_urls" says "compare" and "url": it reads web pages, which anyone can write.
    • untrusted-inputThe input takes a URL (input.urls), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.urls): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Audit 2 or 3 URLs (yours and competitors') and compare them side by side: score, P1/P2/P3 counts, blocked crawlers, llms.txt, structured data, text without JavaScript. Needs an API key.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
    • title: Compare 2-3 URLs
  • explain_findingExplain a finding id (e.g.Reads text others writeNo findings

    Why it is in this group

    • The name "explain_finding" says "explain": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Explain a finding id (e.g. access.blocked, robots.disallowed, schema.software_no_offers) in the given language: what it means, why it matters for AI search and how to fix it.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
    • title: Explain a finding
  • list_watched_sitesList the URLs this account monitors, with the frequency, last score and last check time.Reads text others writeNo findings

    Why it is in this group

    • The name "list_watched_sites" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    List the URLs this account monitors, with the frequency, last score and last check time. Needs an API key.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
    • title: List monitored URLs
  • show_ai_crawler_checkCheck one page for AI crawlers and AI search (the same check and limits as audit_url) and show the result as a visual card in apps that render one (ChatGPT, Claude): the score, whi…Reads private dataReads text others writeCan send data outNo findings

    Why it is in this group

    • The name "show_ai_crawler_check" says "show": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "chat": it reads messages.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "url": 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.

    Description, as the server wrote it
    Check one page for AI crawlers and AI search (the same check and limits as audit_url) and show the result as a visual card in apps that render one (ChatGPT, Claude): the score, which AI crawlers are let in or blocked, the costliest finding with its fix and how many findings are locked, by priority. Use it when the user wants to see a site's AI crawler access at a glance; use audit_url for a Markdown report.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
    • title: Show an AI crawler check card

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.

54 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write9
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out6
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__aiseewhy__show_ai_crawler_check"
    ]
  }
}

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.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:21 UTC, unchanged since Nov 20, 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
4
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 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://api.aiseewhy.com/mcp: tools/list returned 8 tools to an anonymous client, including audit_url (write), audit_sitemap (write), crawl_site (write), watch_site (write)

    What this check looks for

Posture changes

  1. Nov 20, 2026
    • Tools that change things, listed without credentials: 3 to 4

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools3 added, 4 changed.+3 added~4 changedView diff
  2. PostureRemote posture changed. Tools that change things, listed without credentials: 3 -> 4.View diff
    • Tools that change things, listed without credentials: 3 to 4
  3. Tools6 changed.~6 changedView diff

Install

Pinned to version 1.2.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http aiseewhy https://api.aiseewhy.com/mcp
claude mcp add --transport http aiseewhy https://api.aiseewhy.com/mcp

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__aiseewhy__explain_finding",
      "mcp__aiseewhy__list_watched_sites"
    ],
    "ask": [
      "mcp__aiseewhy__show_ai_crawler_check",
      "mcp__aiseewhy__audit_url",
      "mcp__aiseewhy__audit_sitemap",
      "mcp__aiseewhy__compare_urls",
      "mcp__aiseewhy__crawl_site",
      "mcp__aiseewhy__find_broken_links",
      "mcp__aiseewhy__watch_site"
    ],
    "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 aiseewhy. Review it before you use it.

Capability tags behind 9 rules
  • mcp__aiseewhy__show_ai_crawler_check private-data, untrusted-input, outbound
  • mcp__aiseewhy__audit_url untrusted-input, outbound
  • mcp__aiseewhy__audit_sitemap untrusted-input
  • mcp__aiseewhy__explain_finding untrusted-input
  • mcp__aiseewhy__compare_urls untrusted-input, outbound
  • mcp__aiseewhy__crawl_site untrusted-input, outbound
  • mcp__aiseewhy__find_broken_links untrusted-input, outbound
  • mcp__aiseewhy__watch_site untrusted-input, outbound
  • mcp__aiseewhy__list_watched_sites untrusted-input

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.aiseewhy/aiseewhy/verify?hash=577e24134e00e4b4c16287cae72174a558a4743071f40f0251ecfa3fd271cf65" | jq -e '.changed == false'

Pinned hash 577e24134e00, from Nov 21, 2026, 10:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/com.aiseewhy/aiseewhy/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for com.aiseewhy/aiseewhy
[![Anlyon Radar](https://radar.anlyon.com/badge/com.aiseewhy/aiseewhy.svg)](https://radar.anlyon.com/servers/com.aiseewhy/aiseewhy)

Source: MCP Registry · repository. Synced Nov 21, 2026, 10:17 UTC.

AISeeWhy MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the AISeeWhy MCP server safe?

No scan can promise that. What its definitions show: 9 tools, 4 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the AISeeWhy MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the AISeeWhy 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 AISeeWhy MCP server have?

9 tools: 4 write, 5 read. audit_url, audit_sitemap, crawl_site, watch_site, show_ai_crawler_check, explain_finding, compare_urls, find_broken_links and 1 more.

Does the AISeeWhy MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the AISeeWhy MCP server send data to outside services?

6 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): show_ai_crawler_check, audit_url, compare_urls, crawl_site, find_broken_links and watch_site.

Has the AISeeWhy MCP server changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 21, 2026. Every change is on this page and in its Atom feed.