stillindexed SEO checkers MCP server
com.stillindexed/seo-checkersstillindexed.comstreamable-httpv1.1.0Scanned
Indexability, robots.txt, sitemap, TLS, domain expiry and Googlebot-vs-browser checks. No account.
11 tools: 7 change things and 4 only read.
- Reads private data · 0
- Reads text others write · 11
- Can send data out · 11
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
7 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 stillindexed SEO checkers MCP server can do
The stillindexed SEO checkers MCP server is published by stillindexed.com, a domain the MCP Registry verified. It has 11 tools. It can create or change data (7 tools: stillindexed_bulk_check, stillindexed_check_tls, stillindexed_check_domain, stillindexed_check_ai_crawlers and 3 more), but cannot delete data. 4 tools only read.
11 tools bring in text other people can write (stillindexed_check_url, stillindexed_bulk_check, stillindexed_check_robots and 8 more); 11 tools can send data out of your system (stillindexed_check_url, stillindexed_bulk_check, stillindexed_check_robots and 8 more).
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, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 9, 2026, version 1.1.0.
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.
11 tools
Changes things 7Claude Code: ask
stillindexed_bulk_checkIndexability check for up to 20 URLs in one call.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.urls): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Indexability check for up to 20 URLs in one call. Order preserved. Invalid URLs become per-row errors; HTTP status stays 200. Counts against the 60 fetches/hour budget, one per URL.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
stillindexed_check_ai_crawlersCheck robots.txt for the 13 tracked AI crawlers (ChatGPT search, Claude, Perplexity, Gemini grounding, and the training crawlers) and report, per crawler, whether the given URL's p…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 Check robots.txt for the 13 tracked AI crawlers (ChatGPT search, Claude, Perplexity, Gemini grounding, and the training crawlers) and report, per crawler, whether the given URL's path is allowed or blocked, naming the deciding group and rule. Also probes the edge once as each of the three AI search crawlers (OAI-SearchBot, Claude-SearchBot, PerplexityBot) against a browser request. Costs up to 5 fetches. Same check as https://stillindexed.com/tools/ai-crawler-checker.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
stillindexed_check_domainDomain registration expiry via RDAP.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 Domain registration expiry via RDAP. Many ccTLDs have no RDAP; the tool says so instead of inventing an expiry.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
stillindexed_check_tlsTLS certificate for the host: days remaining, chain validity, hostname match.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 TLS certificate for the host: days remaining, chain validity, hostname match.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
stillindexed_deindex_triageTriage a domain that disappeared from Google.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 Triage a domain that disappeared from Google. Checks nine causes in crawl-then-index order (domain registration via RDAP, TLS certificate, robots.txt status, robots.txt rule for the homepage, homepage status as Googlebot vs a browser, redirects off the domain, noindex in meta or X-Robots-Tag, canonical to another host, sitemap served and parseable) and returns each as ruled_out, suspect, confirmed or unknown with evidence. Costs 6 fetches. Same check as https://stillindexed.com/tools/deindex-triage.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
stillindexed_generate_seo_skillFetch the URL, robots.txt, sitemap (with index expansion), host variants, a four-persona crawler diff and TLS, then return a SKILL.md an agent can install for that host.Reads text others writeCan send data out1 finding
Why it is in this group
- The name "stillindexed_generate_seo_skill" 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 "stillindexed_generate_seo_skill" 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 "stillindexed_generate_seo_skill" says "generate": a word for a change.
Description, as the server wrote it Fetch the URL, robots.txt, sitemap (with index expansion), host variants, a four-persona crawler diff and TLS, then return a SKILL.md an agent can install for that host. Up to 12 fetches. Same generator as https://stillindexed.com/tools/seo-skill-generator.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
stillindexed_sitemap_auditAudit a sitemap: pass a sitemap URL, or a hostname to use the sitemap robots.txt declares.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 a sitemap: pass a sitemap URL, or a hostname to use the sitemap robots.txt declares. Samples up to 200 listed URLs (evenly across the file; up to 5 children of a sitemap index), fetches each with the stillindexedbot user agent, and flags non-200, redirected, noindex, blocked by robots.txt for Googlebot, and canonicalized elsewhere. Also reports identical and future-dated lastmod values. Takes up to 90 seconds. Separate allowance of 2 audits per IP per hour, not the 60-fetch budget. Same audit as https://stillindexed.com/tools/sitemap-audit.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
Only reads 4Show 4 read-only tools
stillindexed_check_robotsValidate a robots.txt with RFC 9309 and Google's parsing rules.Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "validate": a word for reading.
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.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Validate a robots.txt with RFC 9309 and Google's parsing rules. Give url to fetch the live file, or content to test a pasted one, plus proposed to diff a second version. For each path or URL (up to 100, or use_sitemap to read them from the file's Sitemap line) it reports allowed or blocked for Googlebot, Googlebot-Image, Bingbot, GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, Claude-SearchBot, PerplexityBot, Google-Extended and CCBot, with the deciding rule and its line number, plus lints (unsupported fields, 500 KiB limit, BOM, HTTP status semantics). With proposed, changes lists only the verdicts that flip. Same check as https://stillindexed.com/tools/robots-txt-tester.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
stillindexed_check_sitemapFetch a sitemap (or the host's /sitemap.xml) and report status, XML validity, and URL count.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 Fetch a sitemap (or the host's /sitemap.xml) and report status, XML validity, and URL count.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
stillindexed_check_urlFetch one URL and report HTTP status, redirect chain, meta robots, X-Robots-Tag, canonical, title, H1, and whether it is indexable.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 name "stillindexed_check_url" says "url": it reads web pages, which anyone can write.
- 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 Fetch one URL and report HTTP status, redirect chain, meta robots, X-Robots-Tag, canonical, title, H1, and whether it is indexable. Same check as https://stillindexed.com/tools/indexability-checker.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
stillindexed_crawler_diffFetch the same URL as Googlebot, Bingbot, GPTBot and a browser, then compare status, indexability directives and content.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "stillindexed_crawler_diff" says "diff": 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 Fetch the same URL as Googlebot, Bingbot, GPTBot and a browser, then compare status, indexability directives and content. Costs 4 fetches.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: 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.
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 write11
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out11
- 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, 18:47 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
- 7
- 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 7 tools that change things (7 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://api.stillindexed.com/mcp: tools/list returned 11 tools to an anonymous client, including stillindexed_bulk_check (write), stillindexed_check_tls (write), stillindexed_check_domain (write), stillindexed_check_ai_crawlers (write), stillindexed_generate_seo_skill (write) and 2 more
Findings
Matches of fixed checks, with the text they matched.
The server marks "stillindexed_generate_seo_skill" 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 "stillindexed_generate_seo_skill" says "generate": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools2 added, 1 changed.+2 added~1 changedView diff
- Added:stillindexed_deindex_triageChanges things
- Added:stillindexed_sitemap_auditChanges things
- Changed:stillindexed_check_robotsOnly readsdescriptioninputSchema
Install
Pinned to version 1.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http seo-checkers https://api.stillindexed.com/mcpclaude mcp add --transport http seo-checkers https://api.stillindexed.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": [],
"ask": [
"mcp__seo-checkers__stillindexed_check_url",
"mcp__seo-checkers__stillindexed_bulk_check",
"mcp__seo-checkers__stillindexed_check_robots",
"mcp__seo-checkers__stillindexed_check_sitemap",
"mcp__seo-checkers__stillindexed_check_tls",
"mcp__seo-checkers__stillindexed_check_domain",
"mcp__seo-checkers__stillindexed_crawler_diff",
"mcp__seo-checkers__stillindexed_check_ai_crawlers",
"mcp__seo-checkers__stillindexed_generate_seo_skill",
"mcp__seo-checkers__stillindexed_deindex_triage",
"mcp__seo-checkers__stillindexed_sitemap_audit"
],
"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 seo-checkers. Review it before you use it.
Capability tags behind 11 rules
- mcp__seo-checkers__stillindexed_check_url untrusted-input, outbound
- mcp__seo-checkers__stillindexed_bulk_check untrusted-input, outbound
- mcp__seo-checkers__stillindexed_check_robots untrusted-input, outbound
- mcp__seo-checkers__stillindexed_check_sitemap untrusted-input, outbound
- mcp__seo-checkers__stillindexed_check_tls untrusted-input, outbound
- mcp__seo-checkers__stillindexed_check_domain untrusted-input, outbound
- mcp__seo-checkers__stillindexed_crawler_diff untrusted-input, outbound
- mcp__seo-checkers__stillindexed_check_ai_crawlers untrusted-input, outbound
- mcp__seo-checkers__stillindexed_generate_seo_skill untrusted-input, outbound
- mcp__seo-checkers__stillindexed_deindex_triage untrusted-input, outbound
- mcp__seo-checkers__stillindexed_sitemap_audit 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.stillindexed/seo-checkers/verify?hash=90d8d73e3c1ce23dc3def1269cfca5dbe74cf9d64cc69b6d50fa5598dcba80a5" | jq -e '.changed == false'Pinned hash 90d8d73e3c1c, from Nov 9, 2026, 06:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.stillindexed/seo-checkers/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.stillindexed/seo-checkers)Source: MCP Registry. Synced Oct 25, 2026, 18:27 UTC.
stillindexed SEO checkers MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the stillindexed SEO checkers MCP server safe?
- No scan can promise that. What its definitions show: 11 tools, 7 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 stillindexed SEO checkers MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the stillindexed SEO checkers 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 stillindexed SEO checkers MCP server have?
- 11 tools: 7 write, 4 read. stillindexed_bulk_check, stillindexed_check_tls, stillindexed_check_domain, stillindexed_check_ai_crawlers, stillindexed_generate_seo_skill, stillindexed_deindex_triage, stillindexed_sitemap_audit, stillindexed_check_url and 3 more.
Does the stillindexed SEO checkers MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the stillindexed SEO checkers MCP server send data to outside services?
- 11 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): stillindexed_check_url, stillindexed_bulk_check, stillindexed_check_robots, stillindexed_check_sitemap, stillindexed_check_tls, stillindexed_check_domain and 5 more.
Has the stillindexed SEO checkers MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Oct 25, 2026. Every change is on this page and in its Atom feed.