AEO Inspector MCP server
com.aeoinspector/aeo-inspectoraeoinspector.comstreamable-httpv2.2.0Scanned
AEO scan, 16-engine AI report and one-domain security + AEO report with fixes (x402 USDC).
4 tools: 4 change things.
- Reads private data · 0
- Reads text others write · 3
- Can send data out · 3
- 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.
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 AEO Inspector MCP server can do
The AEO Inspector MCP server is published by aeoinspector.com, a domain the MCP Registry verified. It has 4 tools. It can create or change data (4 tools: pricing, scan_site, full_report and domain_report), but cannot delete data. None of its tools only reads.
3 tools bring in text other people can write (scan_site, full_report and domain_report); 3 tools can send data out of your system (scan_site, full_report and domain_report).
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.
Last scanned Nov 12, 2026, version 2.2.0.
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.
4 tools
Changes things 4Claude Code: ask
domain_reportOne-domain report: runs the OrionCMD site audit (TLS from CT logs, DNS/DNSSEC/CAA, RDAP expiry, SPF/DMARC/DKIM/MTA-STS, security headers, security.txt) and the AEO Inspector deep s…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 One-domain report: runs the OrionCMD site audit (TLS from CT logs, DNS/DNSSEC/CAA, RDAP expiry, SPF/DMARC/DKIM/MTA-STS, security headers, security.txt) and the AEO Inspector deep scan (AI crawler access, bot-vs-browser diff, agent-ready checks) for one domain. Returns both grades and one merged, priority-sorted fixes list (paste-ready DNS records, registrar steps, robots.txt/llms.txt/JSON-LD) with a shell command to verify each, plus a report_url kept 30 days. Not charged if any part can't run. Costs $2 USDC per call via x402 (payment in _meta["x402/payment"]); invalid input or a failed run returns an error and is not charged.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
- idempotentHint: false
- title: One-domain security + AEO report
full_report16-engine AI visibility report: five category questions, each asked 3 times (240 answers), to ChatGPT, Microsoft Copilot, Gemini, Claude, Grok, Google AI Overviews, Google AI Mode,…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 16-engine AI visibility report: five category questions, each asked 3 times (240 answers), to ChatGPT, Microsoft Copilot, Gemini, Claude, Grok, Google AI Overviews, Google AI Mode, Perplexity, Meta AI, DeepSeek, Qwen, Mistral, GLM, MiniMax, Exa Answer and You.com. Returns per-engine answers, mention rate, citations of the site (own domain in the returned sources), a visibility score, competitor share of mentions (overall and per engine), the sources engines cited, and a report_url. Takes 2-4 minutes. Not charged unless at least 12 of 16 engines answer. Costs $9 USDC per call via x402 (payment in _meta["x402/payment"]); invalid input or a failed run returns an error and is not charged.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
- idempotentHint: false
- title: 16-engine AI visibility report
pricingFree.No 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.
Description, as the server wrote it Free. Prices of the paid tools and HTTP endpoints, the payment network (Base) and address. No input, no network request, no payment.
Annotations the server declares
- title: Prices (free)
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
- destructiveHint: false
scan_siteDeep AEO scan of a website: fetches the homepage as a browser, Googlebot, OAI-SearchBot, GPTBot, ClaudeBot and PerplexityBot and diffs what each gets (JS shells, stale prerender sn…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 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 Deep AEO scan of a website: fetches the homepage as a browser, Googlebot, OAI-SearchBot, GPTBot, ClaudeBot and PerplexityBot and diffs what each gets (JS shells, stale prerender snapshots, cloaking-like gaps), diagnoses Cloudflare AI-bot blocks (dashboard setting + WAF Skip rule), detects Base44/Replit/Lovable, reads robots.txt rules for 21 AI crawlers, crawls up to 9 more pages from the sitemap, validates JSON-LD (Organization, LocalBusiness, Product, FAQPage, Article, SoftwareApplication), checks Wikidata/sameAs entity signals, freshness, question-style headings, TTFB and HTML size, and asks Perplexity one category question. Checks agent files (llms.txt, MCP server card or /mcp, OpenAPI, /.well-known/x402 or a 402 challenge, JSON-LD Offer pricing, Web Bot Auth key directory). Returns the 100-point score, crawlerAccess (score, per-bot outcome), agentReady (score, pass/fail checks with fixes), prioritized fixes, a result_url, a badge_url and a ready-to-paste kit (llms.txt, robots.txt, JSON-LD). Takes 10-25 seconds. Costs $0.05 USDC per call via x402 (payment in _meta["x402/payment"]); invalid input or a failed run returns an error and is not charged.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
- idempotentHint: false
- title: Deep AEO scan
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 write3
- 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, 18:33 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
- 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.
What this check looks forMatched text
https://aeoinspector.com/mcp: tools/list returned 4 tools to an anonymous client, including pricing (write), scan_site (write), full_report (write), domain_report (write)
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.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 2.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http aeo-inspector https://aeoinspector.com/mcpclaude mcp add --transport http aeo-inspector https://aeoinspector.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": [],
"ask": [
"mcp__aeo-inspector__pricing",
"mcp__aeo-inspector__scan_site",
"mcp__aeo-inspector__full_report",
"mcp__aeo-inspector__domain_report"
],
"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 aeo-inspector. Review it before you use it.
Capability tags behind 3 rules
- mcp__aeo-inspector__scan_site untrusted-input, outbound
- mcp__aeo-inspector__full_report untrusted-input, outbound
- mcp__aeo-inspector__domain_report untrusted-input, 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.aeoinspector/aeo-inspector/verify?hash=d19540360c1905a93a244a26080b1f94a5f22ab9253e05cbdf16c2b832def322" | jq -e '.changed == false'Pinned hash d19540360c19, from Nov 12, 2026, 12:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.aeoinspector/aeo-inspector/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.aeoinspector/aeo-inspector)Source: MCP Registry. Synced Oct 21, 2026, 17:48 UTC.
AEO Inspector MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the AEO Inspector MCP server safe?
- No scan can promise that. What its definitions show: 4 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 AEO Inspector MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the AEO Inspector 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 AEO Inspector MCP server have?
- 4 tools: 4 write. pricing, scan_site, full_report and domain_report.
Does the AEO Inspector MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the AEO Inspector 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): scan_site, full_report and domain_report.
Has the AEO Inspector MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 12, 2026.