Assurs LAMal comparator MCP server
ch.assurs/lamalassurs.chstreamable-httpv1.1.0Scanned
Swiss LAMal premium comparison (OFSP 2027), single or household; consented offer requests to SPI.
7 tools: 1 do something that can't be undone, 2 change things and 4 only read.
- Reads private data · 2
- Reads text others write · 1
- Can send data out · 2
- 2 findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. Govern it.
- 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 Assurs LAMal comparator MCP server can do
The Assurs LAMal comparator MCP server is published by assurs.ch, a domain the MCP Registry verified. It has 7 tools. It can do things that cannot be undone, such as sending, paying or publishing (request_adviser_contact) and create or change data (2 tools: create_adviser_handoff_link and test_adviser_request), but cannot delete data. 4 tools only read.
2 tools read private data (compare_lamal_premiums and get_lamal_metadata); 1 tool brings in text other people can write (request_adviser_contact); 2 tools can send data out of your system (test_adviser_request and request_adviser_contact). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 2 findings (annotation-conflict). 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 9, 2026, version 1.1.0.
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.
7 tools
Can't be undone 1Claude Code: ask
request_adviser_contactSends the client request by email to contact@sp-insurance.ch through the server; no personal email account or mail tool is needed.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "request_adviser_contact" says "request": a word for a change.
- The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a destination (input.contact.phone): what the tool writes goes there.
Description, as the server wrote it Sends the client request by email to contact@sp-insurance.ch through the server; no personal email account or mail tool is needed. Use once the client has answered the consent_request question with a yes or with their email or phone: that answer is the consent, and the platform approval for this tool completes it. Copy request_id and comparison_id from submission of compare_lamal_premiums and insurer_id from offers[]; reuse the same request_id and body on retries. Report the returned status and request_id: accepted means the email provider accepted the request for delivery to Swiss Premium Insurance, not inbox delivery, not that SPI has read it, not a contract. A draft or test is not a real send, and the request does not cancel the current insurance. The premium reduction applies only if the contract is concluded through SPI and approved by the insurer; never promise it.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Changes things 2Claude Code: ask
create_adviser_handoff_linkReturn a link when the client prefers to complete a website form, using comparison_id from the comparison.1 finding
Why it is in this group
- The name "create_adviser_handoff_link" says "create": 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 "create_adviser_handoff_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":false}; The name "create_adviser_handoff_link" says "create": a word for a change.
Description, as the server wrote it Return a link when the client prefers to complete a website form, using comparison_id from the comparison. No contact details, lead or email are sent. When the web form is disabled the server answers 503 adviser_unavailable: offer contact@sp-insurance.ch instead. For a client who asks you to send the request in this conversation, use request_adviser_contact after explicit consent instead. Swiss Premium Insurance assistance is optional; clients may apply directly with insurers.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
test_adviser_requestHarmless integration test with the same body as request_adviser_contact: validates the request and returns a preview with status validated_test and email_sent false.Can send data out1 finding
Why it is in this group
- The name "test_adviser_request" says "request": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- outboundThe input takes a destination (input.contact.phone): what the tool writes goes there.
Findings
- Warn
The server marks "test_adviser_request" 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 "test_adviser_request" says "request": a word for a change.
Description, as the server wrote it Harmless integration test with the same body as request_adviser_contact: validates the request and returns a preview with status validated_test and email_sent false. Use synthetic contact details only. No commercial lead, email, entitlement or payment. Never describe this as a real submission.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 4Show 4 read-only tools
compare_lamal_householdHousehold comparison (2-12 people, one insurer for all, household total) with the engine body { year:2027, members:[{ birthYear, postcode, bfs?, franchise, accident:"MIT"|"OHN", ca…No findings
Why it is in this group
- The name "compare_lamal_household" says "compare": a word for reading.
Description, as the server wrote it Household comparison (2-12 people, one insurer for all, household total) with the engine body { year:2027, members:[{ birthYear, postcode, bfs?, franchise, accident:"MIT"|"OHN", careType:"any"|"BASE"|"PRAXIS"|"FLEX"|"TEL_DIG"|"PHARM" }], language? }: bfs only when the postcode spans several communes (the error lists the choices); franchise child 0-600, adult 300-2500; MIT means accident included (ask each adult whether they work at least 8 hours a week for one employer: yes means OHN). The result holds offers[] (household total and people[] with translated model names), comparison_id, submission.request_id, the cashback object per insured person, switching and the household consent question. Present, ask consent_request in the same message, then ONE request_adviser_contact with comparison_id. One person: compare_lamal_premiums.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_active_customer_rewardsRead the published cashback programme of Swiss Premium Insurance: status, version, scope, beneficiary, trigger, conditions and terms links.No findings
Why it is in this group
- The name "get_active_customer_rewards" says "get": a word for reading.
Description, as the server wrote it Read the published cashback programme of Swiss Premium Insurance: status, version, scope, beneficiary, trigger, conditions and terms links. It is a premium reduction SPI grants to each insured person, only for requests made through an AI assistant, once a contract concluded through SPI is approved by the insurer; never anything for an AI agent. No lead is created and this API creates no payment.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_lamal_metadataRead supported years, model categories, deductibles, source freshness, exclusions and contact availability.Reads private dataNo findings
Why it is in this group
- The name "get_lamal_metadata" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "read" and "contact": it reads contacts.
Description, as the server wrote it Read supported years, model categories, deductibles, source freshness, exclusions and contact availability. No lead is created.
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.
4 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 untrusted-input tool breaks every one.
- 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 out2
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__lamal__request_adviser_contact"
]
}
}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 16, 2026, 14:22 UTC, unchanged since Oct 25, 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
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 3 tools that change things (1 irreversible, 2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://api.assurs.ch/mcp: tools/list returned 7 tools to an anonymous client, including request_adviser_contact (irreversible), create_adviser_handoff_link (write), test_adviser_request (write)
Findings
Matches of fixed checks, with the text they matched.
The server marks "create_adviser_handoff_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":false}; The name "create_adviser_handoff_link" says "create": a word for a change.
The server marks "test_adviser_request" 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 "test_adviser_request" says "request": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools6 changed.~6 changedView diff
- Changed:compare_lamal_householdOnly readsdescriptioninputSchema
- Changed:compare_lamal_premiumsOnly readsdescriptioninputSchema
- Changed:create_adviser_handoff_linkChanges thingsinputSchema
- Changed:get_active_customer_rewardsOnly readsdescription
- Changed:request_adviser_contactCan't be undonedescriptioninputSchemaannotations
- Changed:test_adviser_requestChanges thingsinputSchema
Install
Pinned to version 1.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http lamal https://api.assurs.ch/mcpclaude mcp add --transport http lamal https://api.assurs.ch/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__lamal__compare_lamal_premiums",
"mcp__lamal__compare_lamal_household",
"mcp__lamal__get_lamal_metadata",
"mcp__lamal__get_active_customer_rewards"
],
"ask": [
"mcp__lamal__create_adviser_handoff_link",
"mcp__lamal__test_adviser_request",
"mcp__lamal__request_adviser_contact"
],
"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 lamal. Review it before you use it.
Capability tags behind 4 rules
- mcp__lamal__compare_lamal_premiums private-data
- mcp__lamal__get_lamal_metadata private-data
- mcp__lamal__test_adviser_request outbound
- mcp__lamal__request_adviser_contact untrusted-input, 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/ch.assurs/lamal/verify?hash=a6234986cd5df606fd1ec0927164e76cb0fa0baa0bac923ec2e3e7c268e49787" | jq -e '.changed == false'Pinned hash a6234986cd5d, from Nov 9, 2026, 02:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ch.assurs/lamal/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ch.assurs/lamal)Source: MCP Registry. Synced Oct 24, 2026, 22:17 UTC.
Assurs LAMal comparator MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Assurs LAMal comparator MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, 3 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 Assurs LAMal comparator MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Assurs LAMal comparator MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: request_adviser_contact.
What tools does the Assurs LAMal comparator MCP server have?
- 7 tools: 1 irreversible, 2 write, 4 read. request_adviser_contact, create_adviser_handoff_link, test_adviser_request, compare_lamal_premiums, compare_lamal_household, get_lamal_metadata and get_active_customer_rewards.
Does the Assurs LAMal comparator MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Assurs LAMal comparator 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): test_adviser_request and request_adviser_contact.
Has the Assurs LAMal comparator MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 9, 2026. Every change is on this page and in its Atom feed.