CareRanks Data MCP server
com.careranks/careranks-datacareranks.comstreamable-httpv1.0.0Scanned
CMS quality ratings, payer-negotiated prices, and clinician data for 41K+ US healthcare facilities.
5 tools: 5 only read.
- Reads private data · 1
- 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 CareRanks Data MCP server can do
The CareRanks Data MCP server is published by careranks.com, a domain the MCP Registry verified. It has 5 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
1 tool reads private data (get_hospital_prices); 1 tool brings in text other people can write (get_facility_profile).
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.
5 tools
Only reads 5Show 5 read-only tools
get_facilityLook up one facility by {type, id}.No findings
Why it is in this group
- The name "get_facility" says "get": a word for reading.
Description, as the server wrote it Look up one facility by {type, id}. Returns the index record plus canonical URLs and which detail tools work for it. Hospital ids are CMS CCNs.
get_facility_profileStructured summary for any facility; for hospitals the full profile markdown (quality measures, ratings context) is returned AS THE TEXT CONTENT BLOCK, with metadata (truncation fl…Reads text others writeNo findings
Why it is in this group
- The name "get_facility_profile" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
Description, as the server wrote it Structured summary for any facility; for hospitals the full profile markdown (quality measures, ratings context) is returned AS THE TEXT CONTENT BLOCK, with metadata (truncation flag, full URL) in structuredContent. max_chars bounds the markdown body.
get_hospital_cliniciansClinicians affiliated with a hospital (CMS data): name, specialty, Medicare procedure volumes, Open Payments totals.No findings
Why it is in this group
- The name "get_hospital_clinicians" says "get": a word for reading.
Description, as the server wrote it Clinicians affiliated with a hospital (CMS data): name, specialty, Medicare procedure volumes, Open Payments totals. Available for ~4,570 hospitals (clinicians_tool_available flag). Filter matches name or specialty.
get_hospital_pricesPayer-negotiated rates parsed from a hospital's federally required machine-readable file.Reads private dataNo findings
Why it is in this group
- The name "get_hospital_prices" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "file": it reads files.
Description, as the server wrote it Payer-negotiated rates parsed from a hospital's federally required machine-readable file. Without `drg`: a per-DRG summary (payer count, min/median/max) across every DRG in the file. With `drg` (digits; zero-padded automatically): the individual payer-by-payer rates for that DRG. Available for ~2,060 hospitals (prices_tool_available flag).
search_facilitiesSearch 41K+ US facilities (hospitals, nursing homes, home-health agencies, dialysis centers, health systems) by name and/or city, optionally filtered by state and type.No findings
Why it is in this group
- The name "search_facilities" says "search": a word for reading.
Description, as the server wrote it Search 41K+ US facilities (hospitals, nursing homes, home-health agencies, dialysis centers, health systems) by name and/or city, optionally filtered by state and type. Returns ids usable with the other tools plus capability flags.
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, 18:35 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 careranks-data https://careranks.com/mcpclaude mcp add --transport http careranks-data https://careranks.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__careranks-data__search_facilities",
"mcp__careranks-data__get_facility",
"mcp__careranks-data__get_hospital_prices",
"mcp__careranks-data__get_hospital_clinicians",
"mcp__careranks-data__get_facility_profile"
],
"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 careranks-data. Review it before you use it.
Capability tags behind 2 rules
- mcp__careranks-data__get_hospital_prices private-data
- mcp__careranks-data__get_facility_profile 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.careranks/careranks-data/verify?hash=91101abf6b32be1bc4b34a0cb2194785a0fb2ecb1b3e85645afbd5b024a69c33" | jq -e '.changed == false'Pinned hash 91101abf6b32, from Nov 12, 2026, 20:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.careranks/careranks-data/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.careranks/careranks-data)Source: MCP Registry. Synced Oct 21, 2026, 17:52 UTC.
CareRanks Data MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the CareRanks Data MCP server safe?
- No scan can promise that. What its definitions show: 5 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 CareRanks Data MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the CareRanks Data 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 CareRanks Data MCP server have?
- 5 tools: 5 read. search_facilities, get_facility, get_hospital_prices, get_hospital_clinicians and get_facility_profile.
Does the CareRanks Data MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the CareRanks Data MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the CareRanks Data MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 12, 2026.