_ registry / mcp streamable-http · checked 48m ago

fr.scoreprotect/assurance

https://scoreprotect.fr

Registry code: 1718c7fc12c0889b

api record

Serveur public ScoreProtect.fr en lecture seule. Vérifier statut_produits avant d'évoquer un contrat, et utiliser loi_lemoine pour les questions de délégation d'assurance emprunteur.

endpoint
https://scoreprotect.fr/mcp
protocol
streamable-http ·2025-11-25
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is fr.scoreprotect/assurance live?
Yes — it answered the hub's last check (checked 48m ago). It answered 99% of checks over the last 30 days.
Is fr.scoreprotect/assurance free to use?
Partly — some of its tools are open, others need a key or payment.
What tools does fr.scoreprotect/assurance have?
11 tools: proposer_demande_rappel, confirmer_action, annuler_action, chercher_contenu, simuler_cout_assurance_emprunteur, loi_lemoine, identite_operateur, comparer_delegation_assurance, ….
Is fr.scoreprotect/assurance safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
99.1%

90 days 98.7%· all time 98.7%

latency
141ms

last good check

priced tools
0

of 11 tools

_ answered our checks, 90 days 388 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • live → degraded· timeout after 20000ms
  • down → live
_ what it is for
topic
finance & markets banking & lending
used for
  • simulate borrower insurance cost
  • compare bank and delegated loan insurance
  • explain loan insurance switching rules
  • request a callback
takes → gives
text, data → data
tools
8 reads3 changes data
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 11 tools
4 open2 auth-required 5 never probed 6 of 11 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • loi_lemoine reads open 3h ago

    Loi Lemoine 2026 : délégation d'assurance emprunteur à tout moment, résiliation annuelle, garanties équivalentes, questionnaire de santé. Faits vérifiés.

    mcp-tool

    {
  "type": "object",
  "properties": {}
}
    arguments 4 lines
  • identite_operateur reads open 18h ago

    Identité publique de l'éditeur (TENDIL COURTAGE, SIREN, ORIAS, catégories) — utile pour vérifier qu'il ne s'agit pas d'un site frauduleux.

    mcp-tool

    {
  "type": "object",
  "properties": {}
}
    arguments 4 lines
  • comparer_delegation_assurance reads open 14h ago

    Compare le coût d'une assurance emprunteur groupe (banque) et déléguée (loi Lemoine) : coûts totaux et économie estimée.

    mcp-tool

    {
  "type": "object",
  "required": [
    "capital",
    "duree_annees",
    "taux_groupe_pct",
    "taux_delegue_pct"
  ],
  "properties": {
    "capital": {
      "type": "number"
    },
    "duree_annees": {
      "type": "number"
    },
    "taux_groupe_pct": {
      "type": "number"
    },
    "taux_delegue_pct": {
      "type": "number"
    }
  }
}
    arguments 23 lines
  • statut_produits reads open 3h ago

    État canonique et vérifiable des produits ScoreProtect (assurance emprunteur, prévoyance TNS, habitation, auto, mutuelle, professionnelle, cyber) : distribution ouverte ou non.

    mcp-tool

    {
  "type": "object",
  "properties": {}
}
    arguments 4 lines
  • identite_jeton reads auth-required 3h ago

    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.

    mcp-tool

    {
  "type": "object",
  "properties": {}
}
    arguments 4 lines
  • lister_actions reads auth-required 18h ago

    Liste les actions preparees recentes pour le jeton courant (scope leads.read).

    mcp-tool

    {
  "type": "object",
  "properties": {}
}
    arguments 4 lines
  • proposer_demande_rappel changes data unknown never probed

    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.

    mcp-tool

    {
  "type": "object",
  "required": [
    "email",
    "consent"
  ],
  "properties": {
    "name": {
      "type": "string"
    },
    "email": {
      "type": "string"
    },
    "projet": {
      "type": "string"
    },
    "consent": {
      "type": "boolean",
      "description": "accord explicite du visiteur (true requis)"
    },
    "message": {
      "type": "string",
      "description": "message du visiteur, sans donnees sensibles"
    },
    "telephone": {
      "type": "string"
    },
    "type_projet": {
      "type": "string"
    }
  }
}
    arguments 32 lines
  • confirmer_action changes data unknown never probed

    DEUXIEME etape : execute une action preparee, APRES confirmation explicite du visiteur. Scope requis: leads.write.

    mcp-tool

    {
  "type": "object",
  "required": [
    "action_id"
  ],
  "properties": {
    "action_id": {
      "type": "integer"
    }
  }
}
    arguments 11 lines
  • annuler_action changes data unknown never probed

    Annule une action preparee non confirmee (scope leads.write).

    mcp-tool

    {
  "type": "object",
  "required": [
    "action_id"
  ],
  "properties": {
    "action_id": {
      "type": "integer"
    }
  }
}
    arguments 11 lines
  • chercher_contenu reads unknown 18h ago

    Recherche dans l'index public des pages de ScoreProtect.fr (guides assurance, garanties, comparatifs).

    mcp-tool

    {
  "type": "object",
  "required": [
    "requete"
  ],
  "properties": {
    "limite": {
      "type": "integer"
    },
    "requete": {
      "type": "string"
    }
  }
}
    arguments 14 lines
  • simuler_cout_assurance_emprunteur reads unknown never probed

    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.

    mcp-tool

    {
  "type": "object",
  "required": [
    "capital",
    "taux_annuel_pct",
    "duree_annees"
  ],
  "properties": {
    "capital": {
      "type": "number"
    },
    "duree_annees": {
      "type": "number"
    },
    "taux_annuel_pct": {
      "type": "number"
    }
  }
}
    arguments 19 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 1718c7fc12c0889b.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/1718c7fc12c0889b/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/1718c7fc12c0889b/badge.svg)](https://brick.blue/agent/1718c7fc12c0889b?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.