Recovery TLV MCP server
il.co.recoverytlv/recoverytlvrecoverytlv.co.ilstreamable-httpv1.19.0Scanned
Read-only facts, MSK references and availability snapshots for a physiotherapy clinic in Tel Aviv
15 tools: 2 change things and 13 only read.
- Reads private data · 2
- Reads text others write · 1
- Can send data out · 0
- 2 findings
Tools listed without sign-in. Remote posture
With Anlyon
2 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 Recovery TLV MCP server can do
The Recovery TLV MCP server is published by recoverytlv.co.il, a domain the MCP Registry verified. It has 15 tools. It can create or change data (2 tools: recovery.clinical_decision.patient_fit and recovery.clinical_decision.safety_screen), but cannot delete data. 13 tools only read.
2 tools read private data (recovery.identity.get_clinic and recovery.identity.get_location); 1 tool brings in text other people can write (recovery.navigation.get_live_availability).
The fixed checks matched 2 findings (annotation-conflict and credentials-mention). 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 8, 2026, version 1.19.0.
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.
15 tools
Changes things 2Claude Code: ask
recovery.clinical_decision.patient_fitBounded patient-routing kernel for scope, fit, nonresponse, exercise, phase-aware return-to-sport review and escalation.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 Bounded patient-routing kernel for scope, fit, nonresponse, exercise, phase-aware return-to-sport review and escalation. Missing safety or clinical data returns INSUFFICIENT_DATA; causal claims, prescriptions and autonomous clearance are prohibited.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
recovery.clinical_decision.safety_screenEvaluate explicitly reported red-flag domains.1 finding
Why it is in this group
- The description's first verb is "evaluate": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "recovery.clinical_decision.safety_screen" 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 description's first verb is "evaluate": a word for a change.
Description, as the server wrote it Evaluate explicitly reported red-flag domains. Every domain must be PRESENT, ABSENT, UNKNOWN or NOT_APPLICABLE; omitted or unknown data can never pass the safety gate.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 13Show 13 read-only tools
recovery.clinical_reference.get_evidenceSearch Recovery TLV's published evidence bibliography.No findings
Why it is in this group
- The name "recovery.clinical_reference.get_evidence" says "get": a word for reading.
Description, as the server wrote it Search Recovery TLV's published evidence bibliography. Returns citations and source identifiers without applying them to an individual patient.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
recovery.clinical_reference.get_healing_timelineReturn broad educational tissue-healing phases and uncertainty.No findings
Why it is in this group
- The name "recovery.clinical_reference.get_healing_timeline" says "get": a word for reading.
Description, as the server wrote it Return broad educational tissue-healing phases and uncertainty. Does not generate a post-operative protocol, exercise dose or return date.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
recovery.clinical_reference.get_imaging_contextReturn population-level prevalence data only when the dataset contains the requested age cohort.No findings
Why it is in this group
- The name "recovery.clinical_reference.get_imaging_context" says "get": a word for reading.
Description, as the server wrote it Return population-level prevalence data only when the dataset contains the requested age cohort. Never extrapolates a neighboring cohort, interprets an individual's scan or excludes pathology.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
recovery.clinical_reference.get_outcome_measureReturn educational information about published outcome measures and thresholds.No findings
Why it is in this group
- The name "recovery.clinical_reference.get_outcome_measure" says "get": a word for reading.
Description, as the server wrote it Return educational information about published outcome measures and thresholds. Does not score or diagnose an individual patient.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
recovery.identity.get_clinicReturn canonical Recovery TLV identity and clinician credentials.Reads private data1 finding
Why it is in this group
- The name "recovery.identity.get_clinic" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "return" and "credential": it reads secrets.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...cal Recovery TLV identity and clinician credentials. No clinical inference, pricing calcula..."
Description, as the server wrote it Return canonical Recovery TLV identity and clinician credentials. No clinical inference, pricing calculation or booking action.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
recovery.identity.get_locationReturn canonical address, coordinates, operating hours and contact channels.Reads private dataNo findings
Why it is in this group
- The name "recovery.identity.get_location" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "return" and "contact": it reads contacts.
Description, as the server wrote it Return canonical address, coordinates, operating hours and contact channels. Hours are not live appointment availability.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
recovery.identity.get_pricingReturn the canonical session fee, duration, cancellation policy and factual reimbursement status.No findings
Why it is in this group
- The name "recovery.identity.get_pricing" says "get": a word for reading.
Description, as the server wrote it Return the canonical session fee, duration, cancellation policy and factual reimbursement status. Does not estimate unverified coverage.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
recovery.identity.get_scopeReturn the clinic's canonical inclusions, exclusions and minimum age as factual policy.No findings
Why it is in this group
- The name "recovery.identity.get_scope" says "get": a word for reading.
Description, as the server wrote it Return the clinic's canonical inclusions, exclusions and minimum age as factual policy. Does not decide safety or patient suitability.
Annotations the server declares
- 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 data2
- 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, 18:55 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
- 2
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://recoverytlv.co.il/.well-known/oauth-protected-resource/api/mcp
- Authorization servers
- https://recoverytlv.co.il
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://recoverytlv.co.il/api/mcp: tools/list returned 15 tools to an anonymous client, including recovery.clinical_decision.patient_fit (write), recovery.clinical_decision.safety_screen (write)
Findings
Matches of fixed checks, with the text they matched.
The server marks "recovery.clinical_decision.safety_screen" 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 description's first verb is "evaluate": a word for a change.
The description mentions "credentials".
What this check looks forMatched text
description: "...cal Recovery TLV identity and clinician credentials. No clinical inference, pricing calcula..."
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools3 changed.~3 changedView diff
- Changed:recovery.navigation.get_booking_handoffOnly readsinputSchema
- Changed:recovery.navigation.get_live_availabilityOnly readsinputSchema
- Changed:recovery.navigation.search_conditionsOnly readsinputSchema
Install
Pinned to version 1.19.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http recoverytlv https://recoverytlv.co.il/api/mcpclaude mcp add --transport http recoverytlv https://recoverytlv.co.il/api/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__recoverytlv__recovery_clinical_reference_get_evidence",
"mcp__recoverytlv__recovery_clinical_reference_get_healing_timeline",
"mcp__recoverytlv__recovery_clinical_reference_get_imaging_context",
"mcp__recoverytlv__recovery_clinical_reference_get_outcome_measure",
"mcp__recoverytlv__recovery_identity_get_clinic",
"mcp__recoverytlv__recovery_identity_get_location",
"mcp__recoverytlv__recovery_identity_get_pricing",
"mcp__recoverytlv__recovery_identity_get_scope",
"mcp__recoverytlv__recovery_navigation_get_booking_handoff",
"mcp__recoverytlv__recovery_navigation_get_condition",
"mcp__recoverytlv__recovery_navigation_get_live_availability",
"mcp__recoverytlv__recovery_navigation_get_reimbursement",
"mcp__recoverytlv__recovery_navigation_search_conditions"
],
"ask": [
"mcp__recoverytlv__recovery_clinical_decision_patient_fit",
"mcp__recoverytlv__recovery_clinical_decision_safety_screen"
],
"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 recoverytlv. Review it before you use it.
Capability tags behind 3 rules
- mcp__recoverytlv__recovery_identity_get_clinic private-data
- mcp__recoverytlv__recovery_identity_get_location private-data
- mcp__recoverytlv__recovery_navigation_get_live_availability 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/il.co.recoverytlv/recoverytlv/verify?hash=c21bc4ce3c399beb0b662d28e1e534339d69b41ec2576ba482d69b4d74dc3d61" | jq -e '.changed == false'Pinned hash c21bc4ce3c39, from Nov 8, 2026, 10:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/il.co.recoverytlv/recoverytlv/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/il.co.recoverytlv/recoverytlv)Source: MCP Registry. Synced Oct 21, 2026, 21:17 UTC.
Recovery TLV MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Recovery TLV MCP server safe?
- No scan can promise that. What its definitions show: 15 tools, 2 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Recovery TLV MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Recovery TLV 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 Recovery TLV MCP server have?
- 15 tools: 2 write, 13 read. recovery.clinical_decision.patient_fit, recovery.clinical_decision.safety_screen, recovery.clinical_reference.get_evidence, recovery.clinical_reference.get_healing_timeline, recovery.clinical_reference.get_imaging_context, recovery.clinical_reference.get_outcome_measure, recovery.identity.get_clinic, recovery.identity.get_location and 7 more.
Does the Recovery TLV MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Recovery TLV MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Recovery TLV MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 8, 2026. Every change is on this page and in its Atom feed.