Siteiz MCP server
com.siteiz/siteizsiteiz.comstreamable-httpv1.0.0Scanned
Check which AI crawlers a site allows and see pages the way AI crawlers do. Free, read-only.
8 tools: 2 change things and 6 only read.
- Reads private data · 1
- Reads text others write · 6
- Can send data out · 3
- 2 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.
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 Siteiz MCP server can do
The Siteiz MCP server is published by siteiz.com, a domain the MCP Registry verified. It has 8 tools. It can create or change data (2 tools: get_search_performance and inspect_url_index), but cannot delete data. 6 tools only read.
1 tool reads private data (check_ai_crawlers); 6 tools bring in text other people can write (check_ai_crawlers, view_page_as_ai_crawler, get_ai_visibility_report and 3 more); 3 tools can send data out of your system (check_ai_crawlers, view_page_as_ai_crawler and inspect_url_index). 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 2 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 14, 2026, version 1.0.0.
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.
8 tools
Changes things 2Claude Code: ask
get_search_performanceClicks, impressions, CTR and average position from your connected Google Search Console, by query, page, device or country, for the last N days (data trails by about 3 days).Reads text others write1 finding
Why it is in this group
- The name "get_search_performance" says "get": a word for reading.
- The description's first verb is "click": 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.
Findings
- Warn
The server marks "get_search_performance" 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 "get_search_performance" says "get": a word for reading.
Description, as the server wrote it Clicks, impressions, CTR and average position from your connected Google Search Console, by query, page, device or country, for the last N days (data trails by about 3 days). Needs a Siteiz Pro API key (Authorization: Bearer header).
Annotations the server declares
- title: Get Google Search Console performance
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
inspect_url_indexRuns Google Search Console URL inspection on one page of your site: index verdict, coverage, robots.txt, last crawl, user and Google canonical, plus the page's Siteiz AI readabilit…Reads text others writeCan send data out1 finding
Why it is in this group
- The name "inspect_url_index" says "inspect": 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 name "inspect_url_index" says "inspect" and "url": 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.
Findings
- Warn
The server marks "inspect_url_index" 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 "inspect_url_index" says "inspect": a word for reading.
Description, as the server wrote it Runs Google Search Console URL inspection on one page of your site: index verdict, coverage, robots.txt, last crawl, user and Google canonical, plus the page's Siteiz AI readability score. Needs a Siteiz Pro API key (Authorization: Bearer header).
Annotations the server declares
- title: Inspect a URL's Google index status
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 6Show 6 read-only tools
check_ai_crawlersReads a website's robots.txt and reports, for 11 AI crawlers (GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, Claude-SearchBot, PerplexityBot, Google-Extended, Applebot-Extended, M…Reads private dataReads 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
- private-dataThe description's first sentence says "read" and "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 "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 a website's robots.txt and reports, for 11 AI crawlers (GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, Claude-SearchBot, PerplexityBot, Google-Extended, Applebot-Extended, Meta-ExternalAgent, CCBot, Bytespider), whether each may reach the given page. Separates AI search crawlers (decide if the site appears in ChatGPT, Claude and Perplexity answers) from training crawlers. Also reports llms.txt and declared sitemaps.
Annotations the server declares
- title: Check AI crawler access
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
explain_ai_crawlerExplains what an AI crawler user agent does (operator, purpose, and what blocking it in robots.txt changes).No findings
Why it is in this group
- The name "explain_ai_crawler" says "explain": a word for reading.
Description, as the server wrote it Explains what an AI crawler user agent does (operator, purpose, and what blocking it in robots.txt changes). Pass a name such as GPTBot or OAI-SearchBot, or omit it to list all crawlers Siteiz tracks.
Annotations the server declares
- title: Explain an AI crawler
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_ai_visibility_reportReturns a published, dated Siteiz AI visibility report for a well-known company's homepage (score, grade, pillar scores, top issues).Reads text others writeNo findings
Why it is in this group
- The name "get_ai_visibility_report" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "return" and "issue": it reads issues, which other people can write.
Description, as the server wrote it Returns a published, dated Siteiz AI visibility report for a well-known company's homepage (score, grade, pillar scores, top issues). Omit the company to list all published reports.
Annotations the server declares
- title: Get a published AI visibility report
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_traffic_ranked_fixesJoins your Search Console impressions with your latest Siteiz scan: scanned pages ranked by real Google impressions, each with its AI readability score and open fixes, plus pages w…Reads text others writeNo findings
Why it is in this group
- The name "get_traffic_ranked_fixes" 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.
Description, as the server wrote it Joins your Search Console impressions with your latest Siteiz scan: scanned pages ranked by real Google impressions, each with its AI readability score and open fixes, plus pages with no impressions (possibly not indexed) and high-traffic pages the scan missed. Use it to decide what to fix first. Needs a Siteiz Pro API key (Authorization: Bearer header).
Annotations the server declares
- title: Get fixes ranked by Google traffic
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
list_my_sitesLists the sites in your Siteiz account with their latest AI readability score, open fixes and linked Search Console property.No findings
Why it is in this group
- The name "list_my_sites" says "list": a word for reading.
Description, as the server wrote it Lists the sites in your Siteiz account with their latest AI readability score, open fixes and linked Search Console property. Needs a Siteiz Pro API key (Authorization: Bearer header).
Annotations the server declares
- title: List my Siteiz sites
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
view_page_as_ai_crawlerFetches one page the way most AI crawlers do (plain HTTP, no JavaScript) and reports what they actually receive: title, meta description, canonical, H1, heading count, structured d…Reads text others writeCan send data outNo findings
Why it is in this group
- The name "view_page_as_ai_crawler" says "view": 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 "fetch" and "http": 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 Fetches one page the way most AI crawlers do (plain HTTP, no JavaScript) and reports what they actually receive: title, meta description, canonical, H1, heading count, structured data types, visible word count, token reading cost, and a text preview. Use it to check whether content is visible to AI without JavaScript.
Annotations the server declares
- title: View a page as an AI crawler
- 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.
18 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 write6
- 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.
{
"permissions": {
"deny": [
"mcp__siteiz__check_ai_crawlers"
]
}
}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, 18:47 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
- 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://siteiz.com/mcp: tools/list returned 8 tools to an anonymous client, including get_search_performance (write), inspect_url_index (write)
Posture changes
- Nov 20, 2026
- Tools that change things, listed without credentials: 0 to 2
Findings
Matches of fixed checks, with the text they matched.
The server marks "get_search_performance" 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 "get_search_performance" says "get": a word for reading.
The server marks "inspect_url_index" 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 "inspect_url_index" says "inspect": a word for reading.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Tools that change things, listed without credentials: 0 -> 2.View diff
- Tools that change things, listed without credentials: 0 to 2
Tools4 added.+4 addedView diff
- Added:get_search_performanceChanges things
- Added:get_traffic_ranked_fixesOnly reads
- Added:inspect_url_indexChanges things
- Added:list_my_sitesOnly reads
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http siteiz https://siteiz.com/mcpclaude mcp add --transport http siteiz https://siteiz.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__siteiz__explain_ai_crawler",
"mcp__siteiz__get_ai_visibility_report",
"mcp__siteiz__list_my_sites",
"mcp__siteiz__get_traffic_ranked_fixes"
],
"ask": [
"mcp__siteiz__check_ai_crawlers",
"mcp__siteiz__view_page_as_ai_crawler",
"mcp__siteiz__get_search_performance",
"mcp__siteiz__inspect_url_index"
],
"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 siteiz. Review it before you use it.
Capability tags behind 6 rules
- mcp__siteiz__check_ai_crawlers private-data, untrusted-input, outbound
- mcp__siteiz__view_page_as_ai_crawler untrusted-input, outbound
- mcp__siteiz__get_ai_visibility_report untrusted-input
- mcp__siteiz__get_search_performance untrusted-input
- mcp__siteiz__get_traffic_ranked_fixes untrusted-input
- mcp__siteiz__inspect_url_index 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.siteiz/siteiz/verify?hash=accd3c79c62539b6933af8b7e90ca79e3772d5f6524392733eda4426db25ed3a" | jq -e '.changed == false'Pinned hash accd3c79c625, from Nov 14, 2026, 09:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.siteiz/siteiz/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.siteiz/siteiz)Source: MCP Registry. Synced Oct 21, 2026, 18:04 UTC.
Siteiz MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Siteiz MCP server safe?
- No scan can promise that. What its definitions show: 8 tools, 2 of which can change, send or delete something, and 2 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 Siteiz MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Siteiz 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 Siteiz MCP server have?
- 8 tools: 2 write, 6 read. get_search_performance, inspect_url_index, check_ai_crawlers, view_page_as_ai_crawler, explain_ai_crawler, get_ai_visibility_report, list_my_sites and get_traffic_ranked_fixes.
Does the Siteiz MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Siteiz 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_ai_crawlers, view_page_as_ai_crawler and inspect_url_index.
Has the Siteiz MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 14, 2026. Every change is on this page and in its Atom feed.