Skip to content

SEO Records MCP server

com.seorecords/seo-recordsseorecords.comstreamable-httpv1.3.1Scanned

SEO check of any website and AI crawler access test (access pass), and the full Audit.

5 tools: 2 change things and 3 only read.

Tools: 0 delete, 0 irreversible, 2 write, 3 read.
  • Reads private data · 0
  • Reads text others write · 4
  • Can send data out · 3
  • No findings

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.
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 SEO Records MCP server can do

The SEO Records MCP server is published by seorecords.com, a domain the MCP Registry verified. It has 5 tools. It can create or change data (2 tools: check_ai_crawler_access and get_full_audit_checkout), but cannot delete data. 3 tools only read.

4 tools bring in text other people can write (check_website_seo, check_ai_crawler_access, get_full_audit_checkout and 1 more); 3 tools can send data out of your system (check_website_seo, check_ai_crawler_access and get_full_audit_checkout).

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 9, 2026, version 1.3.1.

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.

5 tools

Changes things 2Claude Code: ask
  • check_ai_crawler_accessChecks whether ChatGPT, Claude, Perplexity, Copilot, Google (Gemini) and Mistral Le Chat can read a website: robots.txt rules for each AI crawler (certain), the home page requested…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
    Checks whether ChatGPT, Claude, Perplexity, Copilot, Google (Gemini) and Mistral Le Chat can read a website: robots.txt rules for each AI crawler (certain), the home page requested as each crawler versus a normal browser (probable — real crawlers come from other IPs), and page-level blockers (noindex, nosnippet, JavaScript-only pages). Nothing is stored. Requires this connector's access pass (€9.90 for 24 hours, or €29 per month). Docs: https://seorecords.com/assistants

    Annotations the server declares

    • title: Can AI assistants read this website?
    • readOnlyHint: true
    • openWorldHint: true
    • idempotentHint: true
  • get_full_audit_checkoutCreates a secure Stripe payment page for the full Audit SEO Records of a website (whole site crawled, 152 signals with their URLs, PDF report, re-check in one click).Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "get_full_audit_checkout" says "get": a word for reading.
    • The description's first verb is "create": 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.
    • untrusted-inputThe description's first sentence says "create" and "website": 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.
    Description, as the server wrote it
    Creates a secure Stripe payment page for the full Audit SEO Records of a website (whole site crawled, 152 signals with their URLs, PDF report, re-check in one click). One-time payment: €9.90 (1,000 pages), €19.90 (2,500), €29.90 (5,000), €39.90 (7,500), €49.90 (10,000). Nothing is charged until the user pays on the Stripe page. Intended for users who ask to buy the full audit. Docs: https://seorecords.com/assistants

    Annotations the server declares

    • title: Payment link for the full Audit SEO Records
    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: true
    • idempotentHint: false
Only reads 3Show 3 read-only tools
  • check_website_seoReads the public home page of a website and a few pages from its sitemap, the way a search engine does, and returns the SEO problems found (duplicate titles and descriptions, thin …Reads text others writeCan send data outNo findings

    Why it is in this group

    • The description's first verb is "read": 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 "check_website_seo" says "website": it reads web pages, which anyone can write.
    • untrusted-inputThe description's first sentence says "read" and "website": 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
    Reads the public home page of a website and a few pages from its sitemap, the way a search engine does, and returns the SEO problems found (duplicate titles and descriptions, thin content, missing h1, noindex in sitemap, robots.txt, sitemap, http/www variants, compression, mixed content…), the Google snippet as it appears today and where Google cuts it, and the fixes the SEO Records corrector would apply. About 10–20 seconds, nothing is stored. Requires this connector's access pass (€9.90 for 24 hours, or €29 per month). Docs: https://seorecords.com/assistants

    Annotations the server declares

    • title: SEO check of a website
    • readOnlyHint: true
    • openWorldHint: true
    • idempotentHint: true
  • get_product_offerReturns what a SEO Records product does, its platforms, its prices and its secure Stripe payment links (the user pays on Stripe).No findings

    Why it is in this group

    • The name "get_product_offer" says "get": a word for reading.
    Description, as the server wrote it
    Returns what a SEO Records product does, its platforms, its prices and its secure Stripe payment links (the user pays on Stripe). Products: seo-records-corrector (fixes SEO at serve time, WordPress/PrestaShop/Joomla/Drupal/PHP, from €199/year), seo-autopilot (writes descriptions, FAQs and internal links from real catalog data, PrestaShop, from €199/year), duo (both modules, from €339/year), seo-outpost (the corrector at the network edge, any hosting, from €199 for a year), geo-seo-records (opens and measures the AI assistants channel, from €490 for a year), effect-seo-records (monthly whole-site crawl and difference over a year, from €149 for a year); all returns every product. Docs: https://seorecords.com/assistants

    Annotations the server declares

    • title: SEO Records products: offer and payment links
    • readOnlyHint: true
    • openWorldHint: false
    • idempotentHint: true
  • read_audit_reportReads an Audit SEO Records report (or an Effect SEO Records monthly crawl) from the private link its buyer received (https://seorecords.com/audit?id=…): status and progress while t…Reads text others writeNo findings

    Why it is in this group

    • The name "read_audit_report" says "read": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "crawl": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Reads an Audit SEO Records report (or an Effect SEO Records monthly crawl) from the private link its buyer received (https://seorecords.com/audit?id=…): status and progress while the crawl runs; once finished, every signal found with its family, severity, number of pages and example URLs, the difference with the previous audit of the same site, and the yearly curve for Effect customers. Pages cited can then be fixed one by one with the SEO Records Corrector connector. Docs: https://seorecords.com/assistants

    Annotations the server declares

    • title: Read a purchased Audit SEO Records report
    • readOnlyHint: true
    • openWorldHint: false
    • idempotentHint: true

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 write4
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.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:46 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.

    Matched text

    https://api.seorecords.com/mcp: tools/list returned 5 tools to an anonymous client, including check_ai_crawler_access (write), get_full_audit_checkout (write)

    What this check looks for

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. Tools2 changed.~2 changedView diff
  2. Tools2 changed.~2 changedView diff

Install

Pinned to version 1.3.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http seo-records https://api.seorecords.com/mcp
claude mcp add --transport http seo-records https://api.seorecords.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__seo-records__get_product_offer",
      "mcp__seo-records__read_audit_report"
    ],
    "ask": [
      "mcp__seo-records__check_website_seo",
      "mcp__seo-records__check_ai_crawler_access",
      "mcp__seo-records__get_full_audit_checkout"
    ],
    "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 seo-records. Review it before you use it.

Capability tags behind 4 rules
  • mcp__seo-records__check_website_seo untrusted-input, outbound
  • mcp__seo-records__check_ai_crawler_access untrusted-input, outbound
  • mcp__seo-records__get_full_audit_checkout untrusted-input, outbound
  • mcp__seo-records__read_audit_report 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.seorecords/seo-records/verify?hash=e38a43386fb844de22eb6aba8272c4076f83ffd0bba5f3e5ed5b204967d03f07" | jq -e '.changed == false'

Pinned hash e38a43386fb8, from Nov 9, 2026, 20:18 UTC.

Watch

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

https://radar.anlyon.com/servers/com.seorecords/seo-records/changes.xml

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

Badge

Anlyon Radar badge for com.seorecords/seo-records
[![Anlyon Radar](https://radar.anlyon.com/badge/com.seorecords/seo-records.svg)](https://radar.anlyon.com/servers/com.seorecords/seo-records)

Source: MCP Registry. Synced Nov 9, 2026, 21:17 UTC.

SEO Records MCP server: questions and answers

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

Is the SEO Records MCP server safe?

No scan can promise that. What its definitions show: 5 tools, 2 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 SEO Records MCP server delete data?

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

Can the SEO Records 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 SEO Records MCP server have?

5 tools: 2 write, 3 read. check_ai_crawler_access, get_full_audit_checkout, check_website_seo, get_product_offer and read_audit_report.

Does the SEO Records MCP server need sign-in or OAuth?

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

Does the SEO Records 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_website_seo, check_ai_crawler_access and get_full_audit_checkout.

Has the SEO Records MCP server changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 9, 2026. Every change is on this page and in its Atom feed.