Server definition
- Hash
- sha256:c12063d05294b1c7cab92b5fdae5e2af8deace2aa9b6682ceda3cbbb25891707
- What it is
- What a remote MCP server returned when asked what it offers: 10 tools
The blob, as servednamed by its sha256
{
"instructions": "Pour les devis d'assurance (MRH/habitation, auto, emprunteur, moto, santé, professionnels, animaux, etc.), appeler get_quote_requirements puis prepare_quote_request avec les vrais noms des champs. Poser uniquement les questions manquantes et ne jamais inventer l'adresse, les coordonnées ou les réponses. Avant de poser une question de consentement supplémentaire, regarder si l'utilisateur a DEJA autorisé explicitement AssurancesLabs à recevoir sa demande de devis et à le contacter. Si oui, citer MOT POUR MOT ce message antérieur dans prepare_quote_request.prior_user_message. Seul prior_permission_reusable=true permet de réutiliser cet accord : après le récapitulatif, appeler submit_quote_request avec consent_origin=prior_explicit_user_message, consent_question vide et le message cité en consent_message, sans inventer une question jamais posée. Sinon, appeler render_quote_consent et demander la réponse canonique dans ChatGPT, sans ouvrir de site partenaire. Une simple recherche de devis ne suffit pas à autoriser le contact. submit_quote_request est une écriture RESTREINTE et désactivée par défaut, enregistrant le lead dans la base AssurancesLabs uniquement. Aucun partenaire n'est appelé pendant la création ; le routage ultérieur reste dans l'admin AssurancesLabs, avec les contrôles existants. Un texte de consentement rapporté n'est pas une preuve native d'un clic utilisateur.",
"tools": [
{
"description": "Compare two or three exact public home-insurance formulas on the same documentary criteria, with conditions, limits, deductibles and source citations. Start with no arguments to discover available formula_ids and coverage_ids. IDs include the document version. Missing cells never inherit product-level facts or another formula. No ranking, price, current availability or personal coverage inference. Only formulas with already-publishable facts are listed.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"coverage_ids": {
"items": {
"maxLength": 300,
"type": "string"
},
"maxItems": 30,
"minItems": 1,
"type": "array",
"uniqueItems": true
},
"formula_ids": {
"items": {
"maxLength": 500,
"type": "string"
},
"maxItems": 3,
"minItems": 2,
"type": "array",
"uniqueItems": true
}
},
"type": "object"
},
"name": "compare_public_insurance_formulas",
"outputSchema": null
},
{
"description": "Returns the AssurancesLabs citation-oriented sources map (same payload as GET /api/ai/sources).",
"inputSchema": {
"additionalProperties": false,
"properties": {},
"type": "object"
},
"name": "get_ai_sources",
"outputSchema": null
},
{
"description": "Public, read-only documentary example: search for leaks versus repair of the pipe in home-insurance archival documents. Returns only previously publishable fact IDs with formula scope, document version and evidence IDs, or abstains. It never confirms current availability, personalized coverage, ranking or price. Source: https://www.assuranceslabs.com/documentation/habitation/composition/guarantee.",
"inputSchema": {
"additionalProperties": false,
"properties": {},
"type": "object"
},
"name": "get_habitation_leak_search",
"outputSchema": null
},
{
"description": "Retrieve one already-publishable documentary fact using an exact fact_id returned by search_insurance_facts. Preserves formula, edition, conditions, uncertainty and source citations. Not found means unavailable in the public corpus, never an exclusion. Cannot access private or unpublished facts.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"fact_id": {
"maxLength": 500,
"type": "string"
}
},
"required": [
"fact_id"
],
"type": "object"
},
"name": "get_insurance_fact",
"outputSchema": null
},
{
"description": "Discover questionnaire fields, conditional rules, accepted values and the internal AssurancesLabs recipient for native LLM intake across insurance types (MRH, PNO, auto, moto, santé, emprunteur, professional, animaux, etc.). No lead creation and no partner handoff.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"insurance_type": {
"description": "Insurance line; 'animaux' is the supported native pilot.",
"maxLength": 60,
"type": "string"
}
},
"required": [
"insurance_type"
],
"type": "object"
},
"name": "get_quote_requirements",
"outputSchema": null
},
{
"description": "Validate a quote draft against the native questionnaire and return missing/invalid questions and the canonical consent prompt. Before asking the user again, inspect any prior explicit instruction in the SAME conversation and supply its EXACT verbatim text as prior_user_message. The server indicates whether that prior statement is explicit enough to reuse; never infer consent from a generic quote search. Read-only and no partner side effects.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"answers": {
"additionalProperties": true,
"type": "object"
},
"insurance_type": {
"maxLength": 60,
"type": "string"
},
"prior_user_message": {
"description": "Optional exact quote of the user's own prior instruction from this same conversation, never an LLM paraphrase, boolean or speculative assent. Server assesses whether it already authorizes AssurancesLabs to register this request and contact the user.",
"maxLength": 1000,
"type": "string"
}
},
"required": [
"insurance_type",
"answers"
],
"type": "object"
},
"name": "prepare_quote_request",
"outputSchema": null
},
{
"description": "Use this AFTER prepare_quote_request returns ready_to_submit=true for a pet insurance quote. Display the review and exact consent question in an interactive card inside ChatGPT, without opening AssurancesLabs. The user can explicitly accept or refuse. This tool only renders UI, it never creates a lead or contacts an insurer. A model-reported click is not signed proof of consent.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"answers": {
"additionalProperties": true,
"type": "object"
},
"insurance_type": {
"maxLength": 60,
"type": "string"
}
},
"required": [
"insurance_type",
"answers"
],
"type": "object"
},
"name": "render_pet_quote_consent",
"outputSchema": null
},
{
"description": "After prepare_quote_request returns ready_to_submit=true for any supported insurance type (MRH, auto, health, loan, professional, etc.), render an interactive consent review within ChatGPT, without Acheel/Assurland redirects. Read-only: it never writes or delivers a lead. The user reviews and answers inside the LLM. The write tool requires separate authorization.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"answers": {
"additionalProperties": true,
"description": "Real questionnaire field IDs from get_quote_requirements, including structured address objects and arrays for multiple-choice.",
"type": "object"
},
"insurance_type": {
"description": "One of the 21 supported verticals or a documented alias such as mrh, auto, pet, home.",
"maxLength": 60,
"type": "string"
}
},
"required": [
"insurance_type",
"answers"
],
"type": "object"
},
"name": "render_quote_consent",
"outputSchema": null
},
{
"description": "Maps an insurance type to the canonical questionnaire deep link and required fields (same as POST /api/ai/quote-intent).",
"inputSchema": {
"additionalProperties": false,
"properties": {
"insurance_type": {
"description": "One of the 21 funnels: habitation, pno, loyers-impayes, decennale, auto, moto, mobilite-douce, sante, prevoyance, vie, gav, scolaire, obseques, dependance, voyage, animaux, protection-juridique, emprunteur, rc-pro, cyber, multirisque-pro. French labels, English names and the vertical slugs of list_insurers (rc_pro, gli, protection_juridique…) are accepted as aliases.",
"type": "string"
},
"intent": {
"description": "Optional intent hint for the agent",
"type": "string"
}
},
"required": [
"insurance_type"
],
"type": "object"
},
"name": "resolve_quote_intent",
"outputSchema": null
},
{
"description": "Search already-publishable French home-insurance documentary facts with explicit domain synonyms (theft/burglary, leak detection, pipe repairs, etc.). All remaining meaningful terms must match; interpretation is returned and an ambiguous plumber/leak question asks for clarification. Start with query such as recherche fuite or vol bijoux; omit query to browse. Results include exact product/formula, dated document version, conditions and source URLs/pages. Other insurance lines are not covered. No match never means excluded coverage; no current offer or personalized recommendation.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"coverage_id": {
"description": "Exact coverage_id from a result.",
"maxLength": 300,
"type": "string"
},
"formula_id": {
"description": "Exact formula_id from a result. Product-level facts are never inherited.",
"maxLength": 300,
"type": "string"
},
"limit": {
"maximum": 20,
"minimum": 1,
"type": "integer"
},
"offset": {
"maximum": 100000,
"minimum": 0,
"type": "integer"
},
"product_id": {
"description": "Exact product_id from a result.",
"maxLength": 300,
"type": "string"
},
"query": {
"maxLength": 200,
"type": "string"
}
},
"type": "object"
},
"name": "search_insurance_facts",
"outputSchema": null
}
]
}Verify it yourself
curl -s https://api.teppi.xyz/v1/evidence/sha256:c12063d05294b1c7cab92b5fdae5e2af8deace2aa9b6682ceda3cbbb25891707 | sha256sum