AssurancesLabs
Public insurance sources, home leak orientation and quote-intent resolution.
Should I use this
Quality & Safety
Findings (4)
- HIGH
- MEDIUMin get_habitation_leak_search
- LOWin resolve_quote_intent
- LOWin compare_public_insurance_formulas
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"assuranceslabs": {
"url": "https://www.assuranceslabs.com/mcp"
}
}
}Remote endpoints
https://www.assuranceslabs.com/mcpstreamable-httpWhat it can do
Tool inventory
Tools (10)
π’search_insurance_facts(query, product_id, formula_id, coverage_id, limit, ...)
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.
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"maxLength": 200
},
"product_id": {
"type": "string",
"maxLength": 300,
"description": "Exact product_id from a result."
},
"formula_id": {
"type": "string",
"maxLength": 300,
"description": "Exact formula_id from a result. Product-level facts are never inherited."
},
"coverage_id": {
"type": "string",
"maxLength": 300,
"description": "Exact coverage_id from a result."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 20
},
"offset": {
"type": "integer",
"minimum": 0,
"maximum": 100000
}
},
"additionalProperties": false
}π’compare_public_insurance_formulas(formula_ids, coverage_ids)
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.
Input Schema
{
"type": "object",
"properties": {
"formula_ids": {
"type": "array",
"items": {
"type": "string",
"maxLength": 500
},
"minItems": 2,
"maxItems": 3,
"uniqueItems": true
},
"coverage_ids": {
"type": "array",
"items": {
"type": "string",
"maxLength": 300
},
"minItems": 1,
"maxItems": 30,
"uniqueItems": true
}
},
"additionalProperties": false
}π’get_insurance_fact(fact_id)
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.
Input Schema
{
"type": "object",
"properties": {
"fact_id": {
"type": "string",
"maxLength": 500
}
},
"required": [
"fact_id"
],
"additionalProperties": false
}π’get_habitation_leak_search
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.
Input Schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}π’get_ai_sources
Returns the AssurancesLabs citation-oriented sources map (same payload as GET /api/ai/sources).
Input Schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}π’get_quote_requirements(insurance_type)
Discover questionnaire fields, conditional rules, accepted values and the internal AssurancesLabs recipient for native LLM intake across insurance types (MRH, PNO, auto, moto, santΓ©, emprunteur, professional, animaux, etc.). No lead creation and no partner handoff.
Input Schema
{
"type": "object",
"properties": {
"insurance_type": {
"type": "string",
"maxLength": 60,
"description": "Insurance line; 'animaux' is the supported native pilot."
}
},
"required": [
"insurance_type"
],
"additionalProperties": false
}π’prepare_quote_request(insurance_type, answers, prior_user_message)
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.
Input Schema
{
"type": "object",
"properties": {
"insurance_type": {
"type": "string",
"maxLength": 60
},
"answers": {
"type": "object",
"additionalProperties": true
},
"prior_user_message": {
"type": "string",
"maxLength": 1000,
"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."
}
},
"required": [
"insurance_type",
"answers"
],
"additionalProperties": false
}π’render_pet_quote_consent(insurance_type, answers)
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.
Input Schema
{
"type": "object",
"properties": {
"insurance_type": {
"type": "string",
"maxLength": 60
},
"answers": {
"type": "object",
"additionalProperties": true
}
},
"required": [
"insurance_type",
"answers"
],
"additionalProperties": false
}π’render_quote_consent(insurance_type, answers)
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.
Input Schema
{
"type": "object",
"properties": {
"insurance_type": {
"type": "string",
"maxLength": 60,
"description": "One of the 21 supported verticals or a documented alias such as mrh, auto, pet, home."
},
"answers": {
"type": "object",
"additionalProperties": true,
"description": "Real questionnaire field IDs from get_quote_requirements, including structured address objects and arrays for multiple-choice."
}
},
"required": [
"insurance_type",
"answers"
],
"additionalProperties": false
}π’resolve_quote_intent(insurance_type, intent)
Maps an insurance type to the canonical questionnaire deep link and required fields (same as POST /api/ai/quote-intent).
Input Schema
{
"type": "object",
"properties": {
"insurance_type": {
"type": "string",
"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_juridiqueβ¦) are accepted as aliases."
},
"intent": {
"type": "string",
"description": "Optional intent hint for the agent"
}
},
"required": [
"insurance_type"
],
"additionalProperties": false
}Community
Evidence