xfix MCP server
ai.xfix/xfixxfix.aistreamable-httpv1.1.1Scanned
Check if AI assistants and shopping agents can read a website or online store
8 tools: 3 change things and 5 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
3 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 xfix MCP server can do
The xfix MCP server is published by xfix.ai, a domain the MCP Registry verified. It has 8 tools. It can create or change data (3 tools: check_store_ai_readiness, check_page_visibility and check_ad_grants_website), but cannot delete data. 5 tools only read.
1 tool reads private data (check_ai_crawler_access); 6 tools bring in text other people can write (check_store_ai_readiness, check_ai_crawler_access, check_page_readability and 3 more); 3 tools can send data out of your system (check_ai_crawler_access, check_page_readability and check_page_visibility). 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 21, 2026, version 1.1.1.
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.
8 tools
Changes things 3Claude Code: ask
check_ad_grants_websiteChecks a nonprofit's public website against the visible parts of Google's Ad Grants website policy: the domain serving the site itself, HTTPS, a findable mission, a physical addres…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 Checks a nonprofit's public website against the visible parts of Google's Ad Grants website policy: the domain serving the site itself, HTTPS, a findable mission, a physical address and registration number, real content on the key pages, working links and donate buttons, a mobile viewport and no ad-serving code. Reads the homepage, About, Programs, Contact and the donate destination without running JavaScript or submitting anything. Returns each policy rule as pass, fail or not checked, with what was seen and the fix. Does not access any Google account; passing does not guarantee approval. Use when the user asks about Google Ad Grants eligibility or their nonprofit website's readiness for it.
Annotations the server declares
- title: Check nonprofit website for Google Ad Grants
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
check_page_visibilityRuns the xfix search check on one public page: fetches it without running JavaScript, checks robots.txt for 9 crawlers, measures mobile speed and reviews text, headings and title.Reads text others writeCan send data out1 finding
Why it is in this group
- 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.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "check_page_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,"openWorldHint":true}; The description's first verb is "run": a word for a change.
Description, as the server wrote it Runs the xfix search check on one public page: fetches it without running JavaScript, checks robots.txt for 9 crawlers, measures mobile speed and reviews text, headings and title. Returns a score out of 100, a grade, coverage, any failed gates and the 5 biggest point losses with fixes. Takes about a minute; if not finished within about 25 seconds, returns a check_id to fetch the result later.
Annotations the server declares
- title: Run xfix search visibility check
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
check_store_ai_readinessChecks whether AI assistants and shopping agents can read an online store.Reads text others write1 finding
Why it is in this group
- The name "check_store_ai_readiness" says "store": 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 "check_store_ai_readiness" 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,"openWorldHint":true}; The name "check_store_ai_readiness" says "store": a word for a change.
Description, as the server wrote it Checks whether AI assistants and shopping agents can read an online store. Fetches the public store pages the user names, without running JavaScript. Returns the store's AI Shopping Readiness Index score if the store is in the Index, which AI crawlers its robots.txt allows, and whether one product page shows price, stock and product structured data in its HTML. Use when the user asks if AI can find, read or shop their store. Does not test checkout or log in. Use when the user gives a store or domain.
Annotations the server declares
- title: Check store AI shopping readiness
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
Only reads 5Show 5 read-only tools
check_ai_crawler_accessReads a site's robots.txt the way 9 crawlers do (Googlebot, Bingbot, Applebot, OAI-SearchBot, ChatGPT-User, Claude-SearchBot, Claude-User, PerplexityBot, Perplexity-User) and retur…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 "chat": it reads messages, 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 Reads a site's robots.txt the way 9 crawlers do (Googlebot, Bingbot, Applebot, OAI-SearchBot, ChatGPT-User, Claude-SearchBot, Claude-User, PerplexityBot, Perplexity-User) and returns which may fetch the given page and the rule that blocks each one. Does not see CDN or firewall rules. Use when the user asks which bots or crawlers can access, crawl or read a site, or asks about robots.txt.
Annotations the server declares
- title: Check AI crawler access
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
check_page_readabilityFetches the public page at the given URL without running JavaScript and reports whether its main text is present in the HTML.Reads 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
- 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 "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 Fetches the public page at the given URL without running JavaScript and reports whether its main text is present in the HTML. Checks one page only. Use when the user asks whether a page's content can be read without JavaScript.
Annotations the server declares
- title: Check page text without JavaScript
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
check_product_pageFetches one public product page without running JavaScript and reports whether the price and stock are in the HTML and which of six product structured data fields are present: pric…Reads text others writeNo findings
Why it is in this group
- The description's first verb is "fetch": 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 "html": it reads web pages, which anyone can write.
Description, as the server wrote it Fetches one public product page without running JavaScript and reports whether the price and stock are in the HTML and which of six product structured data fields are present: price, availability, brand, identifier (gtin or sku), shipping details and aggregate rating. Use when the user gives a product page URL.
Annotations the server declares
- title: Check product page price and schema
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
get_page_visibility_resultReturns the result of an xfix search check started earlier, or its progress if it is still running.No findings
Why it is in this group
- The name "get_page_visibility_result" says "get": a word for reading.
Description, as the server wrote it Returns the result of an xfix search check started earlier, or its progress if it is still running.
Annotations the server declares
- title: Get xfix search result
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
lookup_index_scoreLooks up a store domain in the xfix AI Shopping Readiness Index and returns its published score and the fields shown on the public Index page, or says the store is not in the Index…No findings
Why it is in this group
- The name "lookup_index_score" says "lookup": a word for reading.
Description, as the server wrote it Looks up a store domain in the xfix AI Shopping Readiness Index and returns its published score and the fields shown on the public Index page, or says the store is not in the Index. Does not fetch the store.
Annotations the server declares
- title: Look up AI Shopping Readiness Index score
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
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__xfix__check_ai_crawler_access"
]
}
}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, 18:28 UTC, unchanged since Oct 29, 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
- 3
- 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 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.xfix.ai/mcp: tools/list returned 8 tools to an anonymous client, including check_store_ai_readiness (write), check_page_visibility (write), check_ad_grants_website (write)
Posture changes
- Oct 29, 2026
- Tools that change things, listed without credentials: 2 to 3
Findings
Matches of fixed checks, with the text they matched.
The server marks "check_store_ai_readiness" 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,"openWorldHint":true}; The name "check_store_ai_readiness" says "store": a word for a change.
The server marks "check_page_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,"openWorldHint":true}; The description's first verb is "run": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools1 added.+1 addedView diff
- Added:check_ad_grants_websiteChanges things
PostureRemote posture changed. Tools that change things, listed without credentials: 2 -> 3.View diff
- Tools that change things, listed without credentials: 2 to 3
Install
Pinned to version 1.1.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http xfix https://mcp.xfix.ai/mcpclaude mcp add --transport http xfix https://mcp.xfix.ai/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__xfix__check_product_page",
"mcp__xfix__get_page_visibility_result",
"mcp__xfix__lookup_index_score"
],
"ask": [
"mcp__xfix__check_store_ai_readiness",
"mcp__xfix__check_ai_crawler_access",
"mcp__xfix__check_page_readability",
"mcp__xfix__check_page_visibility",
"mcp__xfix__check_ad_grants_website"
],
"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 xfix. Review it before you use it.
Capability tags behind 6 rules
- mcp__xfix__check_store_ai_readiness untrusted-input
- mcp__xfix__check_ai_crawler_access private-data, untrusted-input, outbound
- mcp__xfix__check_page_readability untrusted-input, outbound
- mcp__xfix__check_product_page untrusted-input
- mcp__xfix__check_page_visibility untrusted-input, outbound
- mcp__xfix__check_ad_grants_website 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/ai.xfix/xfix/verify?hash=6efb6a95ae44285ad4c56f844f1f4f27ece86221b6838a41a87b927404a58273" | jq -e '.changed == false'Pinned hash 6efb6a95ae44, from Nov 21, 2026, 21:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.xfix/xfix/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.xfix/xfix)Source: MCP Registry. Synced Nov 7, 2026, 16:17 UTC.
xfix MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the xfix MCP server safe?
- No scan can promise that. What its definitions show: 8 tools, 3 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 xfix MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the xfix 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 xfix MCP server have?
- 8 tools: 3 write, 5 read. check_store_ai_readiness, check_page_visibility, check_ad_grants_website, check_ai_crawler_access, check_page_readability, check_product_page, get_page_visibility_result and lookup_index_score.
Does the xfix MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the xfix 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_crawler_access, check_page_readability and check_page_visibility.
Has the xfix MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Oct 30, 2026. Every change is on this page and in its Atom feed.