Stay Cost Brain MCP server
com.staycostbrain/stay-cost-brainstaycostbrain.comstreamable-httpv1.0.0Scanned
Tourist and hotel taxes from official sources, worked out night by night for your dates and guests.
5 tools: 3 change things and 2 only read.
- Reads private data · 1
- Reads text others write · 1
- Can send data out · 0
- 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 Stay Cost Brain MCP server can do
The Stay Cost Brain MCP server is published by staycostbrain.com, a domain the MCP Registry verified. It has 5 tools. It can create or change data (3 tools: tourist_tax, place_rules and hotels_link), but cannot delete data. 2 tools only read.
1 tool reads private data (list_places); 1 tool brings in text other people can write (hotels_link).
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 10, 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
hotels_linkA link to live hotel and rental prices for a place or any town and the given dates and guests (Stay22, showing Booking.com, Expedia, Agoda, Vrbo and others).Reads text others write1 finding
Why it is in this group
- The name "hotels_link" says "link": 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 "hotels_link" 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 "hotels_link" says "link": a word for a change.
Description, as the server wrote it A link to live hotel and rental prices for a place or any town and the given dates and guests (Stay22, showing Booking.com, Expedia, Agoda, Vrbo and others). The person sees prices and books there; this tool returns no prices and books nothing. Stay Cost Brain may earn a commission on bookings.
Annotations the server declares
- title: Hotels link
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
place_rulesEvery tourist-tax rule for one researched place: each tax with its authority, legal basis, rates by type of stay, season and area, night caps, exemptions, how it is paid, valid dat…No 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.
Description, as the server wrote it Every tourist-tax rule for one researched place: each tax with its authority, legal basis, rates by type of stay, season and area, night caps, exemptions, how it is paid, valid dates and status (verified, inferred, announced), with source links and dates.
Annotations the server declares
- title: Place rules
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
tourist_taxThe tourist tax for one stay, worked out night by night: each tax that applies (regional and city parts separately), the amount or the range when the star rating or type of stay is…No 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.
Description, as the server wrote it The tourist tax for one stay, worked out night by night: each tax that applies (regional and city parts separately), the amount or the range when the star rating or type of stay is not given, how many nights are charged, how it is paid, announced changes in force on those nights, and the official source and date for each. Accepts a researched place or any town; towns outside the researched places return researched=false. Percentage taxes need room_price_total. Residents', medical and other special exemptions are listed in `rules`, not applied.
Annotations the server declares
- title: Tourist tax
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 2Show 2 read-only tools
get_capabilitiesWhat Stay Cost Brain covers: the researched places, how the tax figures are sourced and dated, what it does not do (no room prices, no booking), and the sister services.No findings
Why it is in this group
- The name "get_capabilities" says "get": a word for reading.
Description, as the server wrote it What Stay Cost Brain covers: the researched places, how the tax figures are sourced and dated, what it does not do (no room prices, no booking), and the sister services.
Annotations the server declares
- title: Get capabilities
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_placesEvery place with a researched tourist-tax table: name, country, today's headline rate, the date it was checked, the next re-check date, the towns that set their own tax, and the pa…Reads private dataNo findings
Why it is in this group
- The name "list_places" says "list": a word for reading.
What it can reach
- private-dataThe description's first sentence says "table": it reads databases.
Description, as the server wrote it Every place with a researched tourist-tax table: name, country, today's headline rate, the date it was checked, the next re-check date, the towns that set their own tax, and the page with every rate and source.
Annotations the server declares
- title: List places
- 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 outbound.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- 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, 18:23 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://staycostbrain.com/mcp: tools/list returned 5 tools to an anonymous client, including tourist_tax (write), place_rules (write), hotels_link (write)
Findings
Matches of fixed checks, with the text they matched.
- Warnhotels_link
The server marks "hotels_link" 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 "hotels_link" says "link": 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 stay-cost-brain https://staycostbrain.com/mcpclaude mcp add --transport http stay-cost-brain https://staycostbrain.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__stay-cost-brain__get_capabilities",
"mcp__stay-cost-brain__list_places"
],
"ask": [
"mcp__stay-cost-brain__tourist_tax",
"mcp__stay-cost-brain__place_rules",
"mcp__stay-cost-brain__hotels_link"
],
"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 stay-cost-brain. Review it before you use it.
Capability tags behind 2 rules
- mcp__stay-cost-brain__list_places private-data
- mcp__stay-cost-brain__hotels_link 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.staycostbrain/stay-cost-brain/verify?hash=2fe5aa1744581a815b662aa8f61196ebf94183c924c36dbef7151e82f733de39" | jq -e '.changed == false'Pinned hash 2fe5aa174458, from Nov 10, 2026, 20:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.staycostbrain/stay-cost-brain/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.staycostbrain/stay-cost-brain)Source: MCP Registry · repository. Synced Oct 29, 2026, 12:17 UTC.
Stay Cost Brain MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Stay Cost Brain MCP server safe?
- No scan can promise that. What its definitions show: 5 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 Stay Cost Brain MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Stay Cost Brain 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 Stay Cost Brain MCP server have?
- 5 tools: 3 write, 2 read. tourist_tax, place_rules, hotels_link, get_capabilities and list_places.
Does the Stay Cost Brain MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Stay Cost Brain MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Stay Cost Brain MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 10, 2026.