Site Check MCP server
com.modernmustardseed/site-checkmodernmustardseed.comstreamable-httpv1.0.0Scanned
Public website health scan, AI-crawler and structured-data readiness, and a local presence score.
4 tools: 2 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 3
- Can send data out · 3
- 1 finding
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 Site Check MCP server can do
The Site Check MCP server is published by modernmustardseed.com, a domain the MCP Registry verified. It has 4 tools. It can create or change data (2 tools: scan_website and score_local_presence), but cannot delete data. 2 tools only read.
3 tools bring in text other people can write (scan_website, check_ai_search_readiness and score_local_presence); 3 tools can send data out of your system (scan_website, check_ai_search_readiness and score_local_presence).
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 17, 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.
4 tools
Changes things 2Claude Code: ask
scan_websiteRun a measured health check of a public website homepage: speed (server response, page weight, scripts, image formats), security (HTTPS, certificate expiry, security headers), doma…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 "scan_website" 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 "run": a word for a change.
Description, as the server wrote it Run a measured health check of a public website homepage: speed (server response, page weight, scripts, image formats), security (HTTPS, certificate expiry, security headers), domain registration expiry, email authentication (MX, SPF, DMARC), search basics (title, description, headings, indexability, sitemap), AI search readiness (structured data, AI crawler rules, llms.txt) and contact paths (tap to call, forms, analytics). Every result is measured, not judged by a model, and each warn or fail comes with a fix and an effort level. Returns a 0 to 100 website score, the top fixes, and how the page appears in a search result. Results are cached for 24 hours. Use detail "full" to include passing checks.
Annotations the server declares
- title: Scan a website
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
score_local_presenceScore a local business on three pillars, website (45 percent), Google reviews (30 percent) and Google Business Profile (25 percent), and return an overall 0 to 100 score, a letter …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 destination (input.phone): what the tool writes goes there.
Description, as the server wrote it Score a local business on three pillars, website (45 percent), Google reviews (30 percent) and Google Business Profile (25 percent), and return an overall 0 to 100 score, a letter grade, each pillar with its verdict, and the top fixes. The website pillar comes from a live scan when a website is given. Review and profile facts (rating, review count, phone, address, hours) are supplied by the caller from the user or from a public listing; this tool does not look them up. A pillar with no facts is marked unknown and left out of the overall score rather than scored as zero.
Annotations the server declares
- title: Score local presence
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 2Show 2 read-only tools
check_ai_search_readinessCheck whether AI assistants and answer engines can read and quote a public website: which AI crawlers (GPTBot, ClaudeBot, PerplexityBot, Google-Extended and others) its robots.txt …Reads text others writeCan send data outNo findings
Why it is in this group
- The name "check_ai_search_readiness" says "search": 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 "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 Check whether AI assistants and answer engines can read and quote a public website: which AI crawlers (GPTBot, ClaudeBot, PerplexityBot, Google-Extended and others) its robots.txt allows or blocks, whether it publishes llms.txt, which structured data types it declares, how its title and description read, and the search and AI checks with fixes. Shares the 24 hour cache with scan_website.
Annotations the server declares
- title: Check AI search readiness
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
explain_checkExplain one Site Check check by its id (as returned by scan_website): what it measures, the pass and fail thresholds, why it matters, how to fix it, and the typical effort.No findings
Why it is in this group
- The name "explain_check" says "explain": a word for reading.
Description, as the server wrote it Explain one Site Check check by its id (as returned by scan_website): what it measures, the pass and fail thresholds, why it matters, how to fix it, and the typical effort. Static reference, no network access.
Annotations the server declares
- title: Explain a check
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- 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.
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, 19:27 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.
What this check looks forMatched text
https://mcp.modernmustardseed.com/site-check: tools/list returned 4 tools to an anonymous client, including scan_website (write), score_local_presence (write)
Findings
Matches of fixed checks, with the text they matched.
- Warnscan_website
The server marks "scan_website" 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 "run": a word for a change.
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 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http site-check https://mcp.modernmustardseed.com/site-checkclaude mcp add --transport http site-check https://mcp.modernmustardseed.com/site-checkRun 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__site-check__explain_check"
],
"ask": [
"mcp__site-check__scan_website",
"mcp__site-check__check_ai_search_readiness",
"mcp__site-check__score_local_presence"
],
"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 site-check. Review it before you use it.
Capability tags behind 3 rules
- mcp__site-check__scan_website untrusted-input, outbound
- mcp__site-check__check_ai_search_readiness untrusted-input, outbound
- mcp__site-check__score_local_presence 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.modernmustardseed/site-check/verify?hash=64d1d5aa4b633513dd2e6e67a9f1989ca33a8f485a8ceb5b5b73723c6dc237a6" | jq -e '.changed == false'Pinned hash 64d1d5aa4b63, from Nov 17, 2026, 15:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.modernmustardseed/site-check/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.modernmustardseed/site-check)Source: MCP Registry. Synced Oct 21, 2026, 17:59 UTC.
Site Check MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Site Check MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 2 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Site Check MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Site Check 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 Site Check MCP server have?
- 4 tools: 2 write, 2 read. scan_website, score_local_presence, check_ai_search_readiness and explain_check.
Does the Site Check MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Site Check 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_website, check_ai_search_readiness and score_local_presence.
Has the Site Check MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 17, 2026.