CookieInspector MCP server
com.cookieinspector/cookieinspectorcookieinspector.comstreamable-httpv1.0.0Scanned
Check what a site's cookie banner really blocks: CMP, trackers, cookies before consent.
9 tools: 3 change things and 6 only read.
- Reads private data · 0
- Reads text others write · 2
- Can send data out · 2
- 1 finding
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 CookieInspector MCP server can do
The CookieInspector MCP server is published by cookieinspector.com, a domain the MCP Registry verified. It has 9 tools. It can create or change data (3 tools: start_scan, explain_finding and prescan_site), but cannot delete data. 6 tools only read.
2 tools bring in text other people can write (get_scan_summary and get_capabilities); 2 tools can send data out of your system (start_scan and prescan_site).
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 12, 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.
9 tools
Changes things 3Claude Code: ask
explain_findingExplain a CookieInspector finding code (e.g.1 finding
Why it is in this group
- The name "explain_finding" says "explain": a word for reading.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "explain_finding" 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 "explain_finding" says "explain": a word for reading.
Description, as the server wrote it Explain a CookieInspector finding code (e.g. THIRD_PARTY_PRE_CONSENT) or what to check in a named consent platform (e.g. Cookiebot). No network call. Technical findings, not legal advice.
Annotations the server declares
- title: Explain a finding or a consent platform
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
prescan_siteStart a quick, anonymous pre-scan of a public website's home page: HTTP headers and HTML only, no real browser.Can send data outNo findings
Why it is in this group
- The description's first verb is "start": a word for a change.
What it can reach
- 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 Start a quick, anonymous pre-scan of a public website's home page: HTTP headers and HTML only, no real browser. Returns a preScanId to pass to get_prescan_result and a link to the report on cookieinspector.com. CookieInspector works alongside any consent platform; it checks what the banner actually does. Technical findings, not legal advice.
Annotations the server declares
- title: Quick pre-scan of a website
- destructiveHint: false
- idempotentHint: false
- readOnlyHint: false
start_scanStart a full CookieInspector scan with a real browser (before and after the consent click, up to 5 pages) on the connected account.Can send data outNo findings
Why it is in this group
- The name "start_scan" says "start": a word for a change.
What it can reach
- 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 Start a full CookieInspector scan with a real browser (before and after the consent click, up to 5 pages) on the connected account. Optional region: main (US East), us-west, eu-de (Germany, for EU-targeted banners). Uses the plan's monthly scans. Returns a scanId to poll with get_scan_status, then get_scan_summary. Technical findings, not legal advice.
Annotations the server declares
- title: Start a full scan
- destructiveHint: false
- idempotentHint: false
- readOnlyHint: false
Only reads 6Show 6 read-only tools
get_capabilitiesDescribe what CookieInspector checks on a website (cookies and trackers before and after the consent click, banner behaviour, consent platform, Google Consent Mode), which tools wo…Reads text others writeNo findings
Why it is in this group
- The name "get_capabilities" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "describe" and "website": it reads web pages, which anyone can write.
Description, as the server wrote it Describe what CookieInspector checks on a website (cookies and trackers before and after the consent click, banner behaviour, consent platform, Google Consent Mode), which tools work without an account, which need a CookieInspector API key, and the quotas. Call this first when unsure which tool to use. Technical findings, not legal advice.
Annotations the server declares
- title: What CookieInspector can do here
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
get_prescan_resultReturn the result of a pre-scan started with prescan_site: riskScore (0 best, 100 worst, the same scale as the full report), risk level, how many cookies load before consent, up to…No findings
Why it is in this group
- The name "get_prescan_result" says "get": a word for reading.
Description, as the server wrote it Return the result of a pre-scan started with prescan_site: riskScore (0 best, 100 worst, the same scale as the full report), risk level, how many cookies load before consent, up to five trackers by name, the consent platform and its confidence, Google Consent Mode status, three findings, and the report link. This is a header-and-HTML pre-scan, single page; the full scan with a real browser, evidence and fix guide requires a CookieInspector account. Technical findings, not legal advice.
Annotations the server declares
- title: Pre-scan result
- destructiveHint: false
- idempotentHint: true
- readOnlyHint: true
get_scan_findingsThe findings of a scan on the connected account, with severity, the affected resource and the recommendation, up to 25.No findings
Why it is in this group
- The name "get_scan_findings" says "get": a word for reading.
Description, as the server wrote it The findings of a scan on the connected account, with severity, the affected resource and the recommendation, up to 25. Use explain_finding for what a code means. Technical findings, not legal advice.
Annotations the server declares
- title: Scan findings
- destructiveHint: false
- idempotentHint: true
- readOnlyHint: true
get_scan_statusStatus of a scan on the connected account: queued, running, completed or failed, with the riskScore (0 best, 100 worst) once done.No findings
Why it is in this group
- The name "get_scan_status" says "get": a word for reading.
Description, as the server wrote it Status of a scan on the connected account: queued, running, completed or failed, with the riskScore (0 best, 100 worst) once done. Technical findings, not legal advice.
Annotations the server declares
- title: Scan status
- destructiveHint: false
- idempotentHint: true
- readOnlyHint: true
get_scan_summarySummary of a completed scan on the connected account: risk score (0 best, 100 worst), verdict, banner and consent platform, cookie and tracker counts, the top issues and the report…Reads text others writeNo findings
Why it is in this group
- The name "get_scan_summary" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "issue": it reads issues, which other people can write.
Description, as the server wrote it Summary of a completed scan on the connected account: risk score (0 best, 100 worst), verdict, banner and consent platform, cookie and tracker counts, the top issues and the report link. Technical findings, not legal advice.
Annotations the server declares
- title: Scan summary
- destructiveHint: false
- idempotentHint: true
- readOnlyHint: true
list_scansThe most recent scans on the connected account, newest first (up to 20), each with its riskScore (0 best, 100 worst).No findings
Why it is in this group
- The name "list_scans" says "list": a word for reading.
Description, as the server wrote it The most recent scans on the connected account, newest first (up to 20), each with its riskScore (0 best, 100 worst). Technical findings, not legal advice.
Annotations the server declares
- title: List recent scans
- destructiveHint: false
- idempotentHint: 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 write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out2
- 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, 18:36 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://api.cookieinspector.com/mcp: tools/list returned 9 tools to an anonymous client, including start_scan (write), explain_finding (write), prescan_site (write)
Findings
Matches of fixed checks, with the text they matched.
- Warnexplain_finding
The server marks "explain_finding" 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 "explain_finding" says "explain": a word for reading.
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 cookieinspector https://api.cookieinspector.com/mcpclaude mcp add --transport http cookieinspector https://api.cookieinspector.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__cookieinspector__get_scan_summary",
"mcp__cookieinspector__get_scan_status",
"mcp__cookieinspector__get_prescan_result",
"mcp__cookieinspector__get_capabilities",
"mcp__cookieinspector__list_scans",
"mcp__cookieinspector__get_scan_findings"
],
"ask": [
"mcp__cookieinspector__start_scan",
"mcp__cookieinspector__explain_finding",
"mcp__cookieinspector__prescan_site"
],
"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 cookieinspector. Review it before you use it.
Capability tags behind 4 rules
- mcp__cookieinspector__get_scan_summary untrusted-input
- mcp__cookieinspector__start_scan outbound
- mcp__cookieinspector__get_capabilities untrusted-input
- mcp__cookieinspector__prescan_site 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.cookieinspector/cookieinspector/verify?hash=4edee7f59a2afc32c16a747a2be34b96f8a4edb94939e627e96d18a582014e79" | jq -e '.changed == false'Pinned hash 4edee7f59a2a, from Nov 12, 2026, 23:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.cookieinspector/cookieinspector/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.cookieinspector/cookieinspector)Source: MCP Registry. Synced Oct 21, 2026, 17:53 UTC.
CookieInspector MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the CookieInspector MCP server safe?
- No scan can promise that. What its definitions show: 9 tools, 3 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 CookieInspector MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the CookieInspector 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 CookieInspector MCP server have?
- 9 tools: 3 write, 6 read. start_scan, explain_finding, prescan_site, get_scan_summary, get_scan_status, get_prescan_result, get_capabilities, list_scans and 1 more.
Does the CookieInspector MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the CookieInspector MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): start_scan and prescan_site.
Has the CookieInspector MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 12, 2026.