AI Search Kit MCP server
com.modernmustardseed/ai-search-kitmodernmustardseed.comstreamable-httpv1.0.0Scanned
Audits AI-crawler access, structured data and llms.txt on a site, and drafts the fixes.
5 tools: 3 change things and 2 only read.
- Reads private data · 1
- Reads text others write · 3
- 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 AI Search Kit MCP server can do
The AI Search Kit MCP server is published by modernmustardseed.com, a domain the MCP Registry verified. It has 5 tools. It can create or change data (3 tools: audit_ai_readiness, generate_local_business_schema and generate_llms_txt), but cannot delete data. 2 tools only read.
1 tool reads private data (check_entity_consistency); 3 tools bring in text other people can write (audit_ai_readiness, generate_llms_txt and check_entity_consistency); 3 tools can send data out of your system (audit_ai_readiness, generate_local_business_schema and generate_llms_txt). 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.
Last scanned Nov 13, 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.
5 tools
Changes things 3Claude Code: ask
audit_ai_readinessAudit one public web page for what AI answer engines and their crawlers rely on.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 Audit one public web page for what AI answer engines and their crawlers rely on. Reads the page plus its site's robots.txt, llms.txt and sitemap, then reports: for each AI crawler and control token (OAI-SearchBot, ChatGPT-User, GPTBot, Claude-SearchBot, Claude-User, ClaudeBot, PerplexityBot, Perplexity-User, Googlebot, Google-Extended, Applebot, Applebot-Extended) whether robots.txt allows it on this page under RFC 9309 matching; noindex and nosnippet directives; JSON-LD validity against the schema.org vocabulary and Google's LocalBusiness rules; whether the name, phone and address in the markup also appear on the visible page; llms.txt format; canonical tag; and sitemap. Every finding cites the public spec or vendor document behind it, with the date it was read. Results are cached for 10 minutes.
Annotations the server declares
- title: Audit AI search readiness
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
generate_llms_txtWrite an llms.txt file in the llmstxt.org format: an H1 with the site name, a blockquote summary, optional details, H2 sections of "- [title](url): note" links, and an Optional sec…Reads text others writeCan send data out1 finding
Why it is in this group
- The name "generate_llms_txt" 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 input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "generate_llms_txt" 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_llms_txt" says "generate": a word for a change.
Description, as the server wrote it Write an llms.txt file in the llmstxt.org format: an H1 with the site name, a blockquote summary, optional details, H2 sections of "- [title](url): note" links, and an Optional section for secondary pages. Give url to build it from the live site (home page, sitemap, and up to 30 pages' own titles and meta descriptions, honoring the site's robots.txt and skipping noindex pages), or give site_name and sections to build it from your own facts; supplied fields override what is read from the site. The result is checked against the format before it is returned. Nothing is published.
Annotations the server declares
- title: Generate llms.txt
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
generate_local_business_schemaTurn a local business's facts into schema.org JSON-LD.Can send data out1 finding
Why it is in this group
- The name "generate_local_business_schema" 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
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "generate_local_business_schema" 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":false}; The name "generate_local_business_schema" says "generate": a word for a change.
Description, as the server wrote it Turn a local business's facts into schema.org JSON-LD. Chooses the most specific LocalBusiness subtype from business_type (for example "roofing company" becomes RoofingContractor) or takes schema_type as given, writes only properties schema.org defines for that type, formats hours, phone and 24 hour or closed days the way Google documents, then validates the output against the schema.org vocabulary. Returns the JSON-LD, a ready-to-paste script tag, the type chosen with alternatives, and cited notes on anything left out. No network access; nothing is published.
Annotations the server declares
- title: Generate LocalBusiness schema
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 2Show 2 read-only tools
check_entity_consistencyCompare a business's name, phone, street, city, region and postal code across up to 8 sources, such as its website, Google Business Profile, Facebook page and directory listings.Reads private dataReads text others writeNo findings
Why it is in this group
- The description's first verb is "compare": a word for reading.
What it can reach
- private-dataThe description's first sentence says "compare" and "directory": it reads files.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "compare" and "website": it reads web pages, which anyone can write.
Description, as the server wrote it Compare a business's name, phone, street, city, region and postal code across up to 8 sources, such as its website, Google Business Profile, Facebook page and directory listings. For each source give a url to read (JSON-LD first, then tap-to-call links and page text) and/or the facts shown on it; supplied facts win, and are needed for sites that block automated readers. Formats are normalized ("123 North Main Street, Suite 4" matches "123 N Main St Ste 4", "(406) 555-0100" matches "+1 406-555-0100"), then each field is reported as consistent, variant or mismatch, with the exact fixes. Give business to compare against a canonical record instead of the majority.
Annotations the server declares
- title: Check entity consistency
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
validate_structured_dataValidate pasted JSON-LD against the schema.org vocabulary (every type, property, domain, range and enumeration value) and Google's documented rules for LocalBusiness and Organizati…No findings
Why it is in this group
- The name "validate_structured_data" says "validate": a word for reading.
Description, as the server wrote it Validate pasted JSON-LD against the schema.org vocabulary (every type, property, domain, range and enumeration value) and Google's documented rules for LocalBusiness and Organization markup: required name and address, recommended properties, hh:mm:ss hours, 5 decimal coordinates, priceRange length, self-serving reviews, sameAs. Accepts one block, several blocks, or the script tags around them. Each issue cites its source. No network access.
Annotations the server declares
- title: Validate structured data
- 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.
9 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 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.
{
"permissions": {
"deny": [
"mcp__ai-search-kit__check_entity_consistency"
]
}
}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, 18:42 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
- 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.modernmustardseed.com/ai-search-kit: tools/list returned 5 tools to an anonymous client, including audit_ai_readiness (write), generate_local_business_schema (write), generate_llms_txt (write)
Findings
Matches of fixed checks, with the text they matched.
The server marks "generate_local_business_schema" 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":false}; The name "generate_local_business_schema" says "generate": a word for a change.
The server marks "generate_llms_txt" 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_llms_txt" says "generate": 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 ai-search-kit https://mcp.modernmustardseed.com/ai-search-kitclaude mcp add --transport http ai-search-kit https://mcp.modernmustardseed.com/ai-search-kitRun 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__ai-search-kit__check_entity_consistency",
"mcp__ai-search-kit__validate_structured_data"
],
"ask": [
"mcp__ai-search-kit__audit_ai_readiness",
"mcp__ai-search-kit__generate_local_business_schema",
"mcp__ai-search-kit__generate_llms_txt"
],
"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 ai-search-kit. Review it before you use it.
Capability tags behind 4 rules
- mcp__ai-search-kit__audit_ai_readiness untrusted-input, outbound
- mcp__ai-search-kit__generate_local_business_schema outbound
- mcp__ai-search-kit__generate_llms_txt untrusted-input, outbound
- mcp__ai-search-kit__check_entity_consistency private-data, 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/com.modernmustardseed/ai-search-kit/verify?hash=093e4e0e55dc8a1ef16ef99fea3b3fc46a2006cb7e9cf453b66671822b3c22d5" | jq -e '.changed == false'Pinned hash 093e4e0e55dc, from Nov 13, 2026, 19:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.modernmustardseed/ai-search-kit/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.modernmustardseed/ai-search-kit)Source: MCP Registry. Synced Oct 21, 2026, 17:59 UTC.
AI Search Kit MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the AI Search Kit MCP server safe?
- No scan can promise that. What its definitions show: 5 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 AI Search Kit MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the AI Search Kit 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 AI Search Kit MCP server have?
- 5 tools: 3 write, 2 read. audit_ai_readiness, generate_local_business_schema, generate_llms_txt, check_entity_consistency and validate_structured_data.
Does the AI Search Kit MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the AI Search Kit 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): audit_ai_readiness, generate_local_business_schema and generate_llms_txt.
Has the AI Search Kit MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 13, 2026.