assurance MCP server
fr.scoreprotect/assurancescoreprotect.frstreamable-httpv1.3.0Scanned
Loi Lemoine, simulateurs assurance emprunteur et statut produits (ORIAS 26000195).
11 tools: 10 change things and 1 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
Anlyon alternative
10 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →What the assurance MCP server can do
The assurance MCP server is published by scoreprotect.fr, a domain the MCP Registry verified. It has 11 tools. It can create or change data (10 tools: proposer_demande_rappel, confirmer_action, annuler_action, lister_actions and 6 more), but cannot delete data. 1 tool only reads.
None of its tools reads private data, brings in text other people write, or sends data out.
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 15, 2026, version 1.3.0.
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.
11 tools
Changes things 10Claude Code: ask
annuler_actionAnnule une action preparee non confirmee (scope leads.write).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.
Description, as the server wrote it Annule une action preparee non confirmee (scope leads.write).
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
chercher_contenuRecherche dans l'index public des pages de ScoreProtect.fr (guides assurance, garanties, comparatifs).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 Recherche dans l'index public des pages de ScoreProtect.fr (guides assurance, garanties, comparatifs).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
confirmer_actionDEUXIEME etape : execute une action preparee, APRES confirmation explicite du visiteur.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.
Description, as the server wrote it DEUXIEME etape : execute une action preparee, APRES confirmation explicite du visiteur. Scope requis: leads.write.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
identite_jetonRenvoie les claims du jeton OAuth fourni (sub, scope, audience, expiration) — permet a un client de verifier son autorisation.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 Renvoie les claims du jeton OAuth fourni (sub, scope, audience, expiration) — permet a un client de verifier son autorisation. Sans jeton : indique comment en obtenir un.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
identite_operateurIdentité publique de l'éditeur (TENDIL COURTAGE, SIREN, ORIAS, catégories) — utile pour vérifier qu'il ne s'agit pas d'un site frauduleux.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 Identité publique de l'éditeur (TENDIL COURTAGE, SIREN, ORIAS, catégories) — utile pour vérifier qu'il ne s'agit pas d'un site frauduleux.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
lister_actionsListe les actions preparees recentes pour le jeton courant (scope leads.read).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 Liste les actions preparees recentes pour le jeton courant (scope leads.read).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
loi_lemoineLoi Lemoine 2026 : délégation d'assurance emprunteur à tout moment, résiliation annuelle, garanties équivalentes, questionnaire de santé.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 Loi Lemoine 2026 : délégation d'assurance emprunteur à tout moment, résiliation annuelle, garanties équivalentes, questionnaire de santé. Faits vérifiés.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
proposer_demande_rappelPREMIERE etape d'une ecriture : prepare une demande de rappel (email + consentement explicite OBLIGATOIRES).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.
Description, as the server wrote it PREMIERE etape d'une ecriture : prepare une demande de rappel (email + consentement explicite OBLIGATOIRES). Retourne un action_id a confirmer par l'utilisateur. Scope requis: leads.write.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
simuler_cout_assurance_emprunteurCalcule le coût d'une assurance emprunteur (total, mensuel moyen, première année) à partir du capital, du taux annuel en % du capital et de la durée.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 Calcule le coût d'une assurance emprunteur (total, mensuel moyen, première année) à partir du capital, du taux annuel en % du capital et de la durée.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
statut_produitsÉtat canonique et vérifiable des produits ScoreProtect (assurance emprunteur, prévoyance TNS, habitation, auto, mutuelle, professionnelle, cyber) : distribution ouverte ou non.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 État canonique et vérifiable des produits ScoreProtect (assurance emprunteur, prévoyance TNS, habitation, auto, mutuelle, professionnelle, cyber) : distribution ouverte ou non.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
Only reads 1Show 1 read-only tool
comparer_delegation_assuranceCompare le coût d'une assurance emprunteur groupe (banque) et déléguée (loi Lemoine) : coûts totaux et économie estimée.No findings
Why it is in this group
- The description's first verb is "compare": a word for reading.
Description, as the server wrote it Compare le coût d'une assurance emprunteur groupe (banque) et déléguée (loi Lemoine) : coûts totaux et économie estimée.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- 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 private-data or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- 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, 18:54 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
- 10
- Protocol version
- 2025-11-25
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://scoreprotect.fr/.well-known/oauth-protected-resource
- 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 10 tools that change things (10 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://scoreprotect.fr/mcp: tools/list returned 11 tools to an anonymous client, including proposer_demande_rappel (write), confirmer_action (write), annuler_action (write), lister_actions (write), identite_jeton (write) and 5 more
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 1.3.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http assurance https://scoreprotect.fr/mcpclaude mcp add --transport http assurance https://scoreprotect.fr/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__assurance__comparer_delegation_assurance"
],
"ask": [
"mcp__assurance__proposer_demande_rappel",
"mcp__assurance__confirmer_action",
"mcp__assurance__annuler_action",
"mcp__assurance__lister_actions",
"mcp__assurance__identite_jeton",
"mcp__assurance__loi_lemoine",
"mcp__assurance__simuler_cout_assurance_emprunteur",
"mcp__assurance__statut_produits",
"mcp__assurance__identite_operateur",
"mcp__assurance__chercher_contenu"
],
"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 assurance. Review it before you use it.
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/fr.scoreprotect/assurance/verify?hash=e9d18e56b95470f84ada581ebfddbc0029c8098be1025f29ee87f56de6c4f548" | jq -e '.changed == false'Pinned hash e9d18e56b954, from Nov 15, 2026, 10:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/fr.scoreprotect/assurance/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/fr.scoreprotect/assurance)Source: MCP Registry. Synced Oct 21, 2026, 18:12 UTC.
assurance MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the assurance MCP server safe?
- No scan can promise that. What its definitions show: 11 tools, 10 of which can change, send or delete something, and 0 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 assurance MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the assurance 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 assurance MCP server have?
- 11 tools: 10 write, 1 read. proposer_demande_rappel, confirmer_action, annuler_action, lister_actions, identite_jeton, loi_lemoine, simuler_cout_assurance_emprunteur, statut_produits and 3 more.
Does the assurance MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the assurance MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the assurance MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 15, 2026.