AEO Research (moved) MCP server
dev.advancelabs/aeo-backlinkadvancelabs.devstreamable-httpv1.0.2Scanned
Moved to dev.advancelabs/aeo-research: AEO audits, AI citation checks, backlinks. No sign-in.
12 tools: 4 change things and 8 only read.
- Reads private data · 1
- Reads text others write · 12
- Can send data out · 9
- 4 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 Research (moved) MCP server can do
The AEO Research (moved) MCP server is published by advancelabs.dev, a domain the MCP Registry verified. It has 12 tools. It can create or change data (4 tools: discover_ranking_prompts, compare_competitor_visibility, verify_page_links and generate_outreach_email), but cannot delete data. 8 tools only read.
1 tool reads private data (extract_contact_info); 12 tools bring in text other people can write (analyze_website_aeo, check_ai_visibility, discover_ranking_prompts and 9 more); 9 tools can send data out of your system (analyze_website_aeo, check_ai_visibility, discover_ranking_prompts and 6 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 4 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.
Last scanned Nov 15, 2026, version 1.0.2.
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.
12 tools
Changes things 4Claude Code: ask
compare_competitor_visibilityRun one Perplexity Sonar query and rank several competitor URLs by whether and where each is cited for the prompt.Reads text others writeCan send data out1 finding
Why it is in this group
- The name "compare_competitor_visibility" says "compare": a word for reading.
- The description's first verb is "run": a word for a change.
- 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 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.
Findings
- Warn
The server marks "compare_competitor_visibility" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "compare_competitor_visibility" says "compare": a word for reading.
Description, as the server wrote it Run one Perplexity Sonar query and rank several competitor URLs by whether and where each is cited for the prompt.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
discover_ranking_promptsGenerate realistic user prompts a site should aim to be cited for on a topic, using Perplexity Sonar.Reads text others writeCan send data out1 finding
Why it is in this group
- The description's first verb is "generate": a word for a change.
- 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.
Findings
- Warn
The server marks "discover_ranking_prompts" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "generate": a word for a change.
Description, as the server wrote it Generate realistic user prompts a site should aim to be cited for on a topic, using Perplexity Sonar. Optionally tests a few of them for live visibility.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
generate_outreach_emailDraft a short, personalized cold outreach email from a contact + context object using your own LLM key (BYOK).Reads text others writeCan send data out1 finding
Why it is in this group
- The name "generate_outreach_email" says "generate": a word for a change.
- 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 name "generate_outreach_email" says "generate" and "email": it writes something other people read.
- outboundThe input takes a URL (input.context.targetUrl): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "generate_outreach_email" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "generate_outreach_email" says "generate": a word for a change.
Description, as the server wrote it Draft a short, personalized cold outreach email from a contact + context object using your own LLM key (BYOK). Returns a subject line and body. The API key is request-scoped and is never persisted or logged.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
verify_page_linksFetch a page and confirm whether it contains a link to the target domain, reporting anchor text and rel attributes (nofollow/sponsored/ugc) and whether the link is dofollow.Reads text others writeCan send data out1 finding
Why it is in this group
- The name "verify_page_links" says "link": a word for a change.
- 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.
Findings
- Warn
The server marks "verify_page_links" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "verify_page_links" says "link": a word for a change.
Description, as the server wrote it Fetch a page and confirm whether it contains a link to the target domain, reporting anchor text and rel attributes (nofollow/sponsored/ugc) and whether the link is dofollow.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 8Show 8 read-only tools
analyze_website_aeoCrawl a URL, parse its HTML and structured data, and score it for answer-engine optimization (AEO).Reads text others writeCan send data outNo findings
Why it is in this group
- The name "analyze_website_aeo" says "analyze": 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 "analyze_website_aeo" says "analyze" and "website": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "crawl": 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 Crawl a URL, parse its HTML and structured data, and score it for answer-engine optimization (AEO). Returns an AEO-focused summary, AI-bot access, and crawl-hint files.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
check_ai_visibilityQuery Perplexity Sonar with a prompt and inspect its citations to determine whether the given URL is cited as a source, and at what rank.Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "query": 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 description's first sentence says "query" and "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 Query Perplexity Sonar with a prompt and inspect its citations to determine whether the given URL is cited as a source, and at what rank.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
check_page_historyReturn a Wayback Machine timeline for a URL: total snapshots, first/last archived dates, and a bounded list of snapshot records with direct archive links.Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "return": 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 description's first sentence says "return" and "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 Return a Wayback Machine timeline for a URL: total snapshots, first/last archived dates, and a bounded list of snapshot records with direct archive links.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
extract_contact_infoFetch a page and extract contact emails (including de-obfuscated and mailto links) and social media handles (Twitter/X, LinkedIn, Facebook, Instagram, GitHub, YouTube).Reads private dataReads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "fetch": a word for reading.
What it can reach
- private-dataThe name "extract_contact_info" says "contact": it reads contacts.
- private-dataThe description's first sentence says "fetch" and "contact": it reads contacts.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "fetch" and "email": it reads inbound email, which other people 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 Fetch a page and extract contact emails (including de-obfuscated and mailto links) and social media handles (Twitter/X, LinkedIn, Facebook, Instagram, GitHub, YouTube).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
find_competitor_link_sourcesApproximate the pages linking to a competitor using free web-search signals (domain mentions and brand mentions).Reads text others writeNo findings
Why it is in this group
- The name "find_competitor_link_sources" says "find": 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 description's first sentence says "web": it reads web pages, which anyone can write.
Description, as the server wrote it Approximate the pages linking to a competitor using free web-search signals (domain mentions and brand mentions). De-duplicates by host and excludes the competitor's own domain. Not a complete backlink index — a free, directional starting point for prospecting.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
find_mentionsFind linked and unlinked mentions of a brand across the web via web search results.Reads text others writeNo findings
Why it is in this group
- The name "find_mentions" says "find": 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 "find_mentions" says "find" and "mention": it reads comments, which other people can write.
- untrusted-inputThe description's first sentence says "find" and "mention": it reads comments, which other people can write.
Description, as the server wrote it Find linked and unlinked mentions of a brand across the web via web search results. When a domain is supplied, classifies each mention as linked (on the brand domain) or unlinked (a third-party page — a potential backlink opportunity).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
find_prospectsFind guest-post, resource-page, and roundup link-building prospects for a topic by running classic outreach footprints through web search and merging the results by host.Reads text others writeNo findings
Why it is in this group
- The name "find_prospects" says "find": 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 description's first sentence says "find" and "post": it reads posts, which other people can write.
Description, as the server wrote it Find guest-post, resource-page, and roundup link-building prospects for a topic by running classic outreach footprints through web search and merging the results by host.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_visibility_reportCombine an AEO audit of a URL with per-prompt AI-visibility checks into a single report with an overall citation rate.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "get_visibility_report" says "get": 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 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 Combine an AEO audit of a URL with per-prompt AI-visibility checks into a single report with an overall citation rate.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: 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.
108 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 write12
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out9
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__aeo-backlink__extract_contact_info"
]
}
}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 15, 2026, 13:21 UTC, unchanged since Oct 31, 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://aeo.advancelabs.dev/api/mcp/backlink/mcp: tools/list returned 7 tools to an anonymous client, including verify_page_links (write), generate_outreach_email (write)
Findings
Matches of fixed checks, with the text they matched.
The server marks "discover_ranking_prompts" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "generate": a word for a change.
The server marks "compare_competitor_visibility" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "compare_competitor_visibility" says "compare": a word for reading.
The server marks "verify_page_links" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "verify_page_links" says "link": a word for a change.
The server marks "generate_outreach_email" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "generate_outreach_email" says "generate": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools5 added.+5 addedView diff
- Added:analyze_website_aeoOnly reads
- Added:check_ai_visibilityOnly reads
- Added:compare_competitor_visibilityChanges things
- Added:discover_ranking_promptsChanges things
- Added:get_visibility_reportOnly reads
Tools3 changed.~3 changedView diff
- Changed:find_competitor_link_sourcesOnly readsdescription
- Changed:find_mentionsOnly readsdescription
- Changed:find_prospectsOnly readsdescription
Install
Pinned to version 1.0.2. Values in angle brackets are yours to fill in.
claude mcp add --transport http aeo-backlink https://aeo.advancelabs.dev/api/mcp/research/mcpclaude mcp add --transport http aeo-backlink https://aeo.advancelabs.dev/api/mcp/research/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__aeo-backlink__find_mentions",
"mcp__aeo-backlink__find_prospects",
"mcp__aeo-backlink__find_competitor_link_sources"
],
"ask": [
"mcp__aeo-backlink__analyze_website_aeo",
"mcp__aeo-backlink__check_ai_visibility",
"mcp__aeo-backlink__discover_ranking_prompts",
"mcp__aeo-backlink__get_visibility_report",
"mcp__aeo-backlink__compare_competitor_visibility",
"mcp__aeo-backlink__verify_page_links",
"mcp__aeo-backlink__extract_contact_info",
"mcp__aeo-backlink__check_page_history",
"mcp__aeo-backlink__generate_outreach_email"
],
"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-backlink. Review it before you use it.
Capability tags behind 12 rules
- mcp__aeo-backlink__analyze_website_aeo untrusted-input, outbound
- mcp__aeo-backlink__check_ai_visibility untrusted-input, outbound
- mcp__aeo-backlink__discover_ranking_prompts untrusted-input, outbound
- mcp__aeo-backlink__get_visibility_report untrusted-input, outbound
- mcp__aeo-backlink__compare_competitor_visibility untrusted-input, outbound
- mcp__aeo-backlink__find_mentions untrusted-input
- mcp__aeo-backlink__find_prospects untrusted-input
- mcp__aeo-backlink__find_competitor_link_sources untrusted-input
- mcp__aeo-backlink__verify_page_links untrusted-input, outbound
- mcp__aeo-backlink__extract_contact_info private-data, untrusted-input, outbound
- mcp__aeo-backlink__check_page_history untrusted-input, outbound
- mcp__aeo-backlink__generate_outreach_email 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/dev.advancelabs/aeo-backlink/verify?hash=25f2ab531c14d7cea2ed5a23a827717b0e2e9d5039654c993d19807eaf0ec5d7" | jq -e '.changed == false'Pinned hash 25f2ab531c14, from Nov 15, 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/dev.advancelabs/aeo-backlink/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/dev.advancelabs/aeo-backlink)Source: MCP Registry · repository. Synced Nov 15, 2026, 18:17 UTC.
AEO Research (moved) MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the AEO Research (moved) MCP server safe?
- No scan can promise that. What its definitions show: 12 tools, 4 of which can change, send or delete something, and 4 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 Research (moved) 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 Research (moved) 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 Research (moved) MCP server have?
- 12 tools: 4 write, 8 read. discover_ranking_prompts, compare_competitor_visibility, verify_page_links, generate_outreach_email, analyze_website_aeo, check_ai_visibility, get_visibility_report, find_mentions and 4 more.
Does the AEO Research (moved) MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the AEO Research (moved) MCP server send data to outside services?
- 9 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): analyze_website_aeo, check_ai_visibility, discover_ranking_prompts, get_visibility_report, compare_competitor_visibility, verify_page_links and 3 more.
Has the AEO Research (moved) MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 15, 2026. Every change is on this page and in its Atom feed.