ScareMap MCP server
app.scaremap/scaremapscaremap.appstreamable-httpv1.0.0Scanned
Find haunted houses, ghost tours and haunted places near you, with visitor ratings.
4 tools: 4 only read.
- Reads private data · 0
- Reads text others write · 1
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
Decide which of this server's tools your agent can use.
- 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 ScareMap MCP server can do
The ScareMap MCP server is published by scaremap.app, a domain the MCP Registry verified. It has 4 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
1 tool brings in text other people can write (scaremap_get_haunt).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
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.
4 tools
Only reads 4Show 4 read-only tools
scaremap_categoriesList every haunt category with its display label and the number of public haunts in it.No findings
Why it is in this group
- The description's first verb is "list": a word for reading.
Description, as the server wrote it List every haunt category with its display label and the number of public haunts in it. Call this first when the user asks what kinds of places ScareMap covers, or to get valid values for the category filter on the other tools. Takes no input.
Annotations the server declares
- title: List haunt categories
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
- destructiveHint: false
scaremap_find_hauntsFind haunted houses, haunt farms, ghost tours, horror escape rooms and haunted places within a radius of a latitude/longitude, nearest first.No findings
Why it is in this group
- The name "scaremap_find_haunts" says "find": a word for reading.
Description, as the server wrote it Find haunted houses, haunt farms, ghost tours, horror escape rooms and haunted places within a radius of a latitude/longitude, nearest first. Call this when the user gives a place, address or coordinates and wants scary things to do nearby. Geocode a place name to lat/lng first; this tool does not search by name. Filter by category, by season, or by minimum visitor ratings. Unrated haunts (review_count 0) have null ratings and are left out when min_stars or min_scare is set. For a whole city or state use scaremap_find_haunts_in_city. For the full record and reviews of one result use scaremap_get_haunt.
Annotations the server declares
- title: Find haunts near a location
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
- destructiveHint: false
scaremap_find_haunts_in_cityList haunts in a US state, or in one city of that state, using the same state and city grouping as the ScareMap location pages.No findings
Why it is in this group
- The name "scaremap_find_haunts_in_city" says "find": a word for reading.
Description, as the server wrote it List haunts in a US state, or in one city of that state, using the same state and city grouping as the ScareMap location pages. Call this when the user names a state or city ("haunted houses in Salem, Massachusetts") and has no coordinates. State accepts a name, a slug or a two-letter code. Results are ordered by review count, then name. If the city is not found, the error lists the cities ScareMap has in that state. To search by distance from a point use scaremap_find_haunts.
Annotations the server declares
- title: Find haunts in a city or state
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
- destructiveHint: false
scaremap_get_hauntGet the full record for one haunt: description, category, season, location, average ratings, and up to 20 of the newest visitor reviews (stars, scare, text, date).Reads text others writeNo findings
Why it is in this group
- The name "scaremap_get_haunt" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "get" and "review": it reads comments, which other people can write.
Description, as the server wrote it Get the full record for one haunt: description, category, season, location, average ratings, and up to 20 of the newest visitor reviews (stars, scare, text, date). Call this after scaremap_find_haunts or scaremap_find_haunts_in_city when the user wants detail on a specific result. Pass the slug from those results, or the haunt id. Reviews are anonymous. A haunt with no reviews returns an empty list.
Annotations the server declares
- title: Get one haunt with reviews
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
- destructiveHint: 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 or outbound.
- Reads private data0
- 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, 18:30 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
- 0
- 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
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
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 scaremap https://www.scaremap.app/mcpclaude mcp add --transport http scaremap https://www.scaremap.app/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__scaremap__scaremap_find_haunts",
"mcp__scaremap__scaremap_find_haunts_in_city",
"mcp__scaremap__scaremap_get_haunt",
"mcp__scaremap__scaremap_categories"
],
"ask": [],
"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 scaremap. Review it before you use it.
Capability tags behind 1 rule
- mcp__scaremap__scaremap_get_haunt 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/app.scaremap/scaremap/verify?hash=3e515a4d7d763f943a05c70cdbeb67f301fc1c4dbab2727fe873ce4cbf80de3c" | jq -e '.changed == false'Pinned hash 3e515a4d7d76, from Nov 12, 2026, 03:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/app.scaremap/scaremap/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/app.scaremap/scaremap)Source: MCP Registry. Synced Oct 21, 2026, 17:45 UTC.
ScareMap MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the ScareMap MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.
Can the ScareMap MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the ScareMap 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 ScareMap MCP server have?
- 4 tools: 4 read. scaremap_find_haunts, scaremap_find_haunts_in_city, scaremap_get_haunt and scaremap_categories.
Does the ScareMap MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the ScareMap MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the ScareMap MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 12, 2026.