Synapze — Financial Intermediary MCP
Server Details
Connect AI agents to licensed insurance brokers in France via MCP. Quotes, appointments, WhatsApp.
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP
- URL
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Tool Definition Quality
Average 4.2/5 across 4 of 4 tools scored. Lowest: 3.6/5.
Each tool has a distinct and clear purpose: finding brokers, getting broker details, listing products, and generating quotes. No overlap or ambiguity.
All tool names follow a consistent verb_noun pattern in snake_case (find_broker, get_broker_info, get_products, get_quote), making them predictable and easy to understand.
With only 4 tools, the set is minimal but covers the essential workflow of a financial intermediary (broker discovery, info, products, quotes). It feels slightly lean but not inappropriate for the scope.
The tool set covers the core lifecycle: find a broker, get branding info, explore products, and request quotes. Missing operations like updating broker info or handling policy management, but these are outside the apparent domain.
Available Tools
4 toolsfind_brokerARead-onlyInspect
Trouver un courtier en assurance / Find a licensed insurance broker in France. Recherche par produit (auto, moto, MRH/habitation, RC Pro, protection juridique, épargne, assurance vie, PER), ville et langue. Search by product type, city, and language. Returns broker name, specialties, DDA compliance status, and connection endpoint.
| Name | Required | Description | Default |
|---|---|---|---|
| city | No | City or zone in France (e.g. 'paris', 'lyon', 'marseille') | |
| ticket | No | Project amount in EUR (for routing large-ticket cases) | |
| product | Yes | Insurance product type: auto, moto, mrh, rc_pro, protection_juridique, epargne, assurance_vie, per | |
| language | No | Preferred language: fr, en | fr |
| sub_specialty | No | Sub-specialty niche within the product (e.g. 'architectes', 'sci_is', 'dirigeants') |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare it as read-only and non-destructive. The description adds value by specifying return fields (name, specialties, DDA compliance, connection endpoint), providing context beyond the annotations without contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is bilingual and front-loaded with the purpose. It uses two efficient sentences covering search criteria and return fields, though the bilingual nature slightly lengthens it.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description mentions return fields but omits details on ticket and sub_specialty parameters, and the 'connection endpoint' is vague. While adequate for basic use, it has gaps for full understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with parameter descriptions. The description adds a list of product values but does not explain ticket or sub_specialty. This provides marginal extra value beyond the schema, earning a baseline 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it finds a licensed insurance broker in France by product, city, and language, and lists the return fields. This distinguishes it from siblings like get_broker_info (specific broker details) and get_products (product listing).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not explicitly tell when to use this tool vs. siblings. It explains what the tool does but lacks guidance on when not to use it or alternative tools, leaving the agent to infer from sibling names.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_broker_infoARead-onlyInspect
Informations et branding du courtier / Broker branding and identity. Returns: company name, logo URL, brand color (#hex), address, postal code, phone, ORIAS number, website, specialties, and DDA compliance status. ALWAYS call this before generating any document (PDF, PPTX, comparison, advisory note) to brand it with the broker's logo, color, name, address, and ORIAS number.
| Name | Required | Description | Default |
|---|---|---|---|
| broker_code | No | Broker code returned by find_broker. Optional in broker-authenticated mode. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint=true and destructiveHint=false. The description adds transparency by specifying exactly what data is returned (company name, logo URL, brand color, etc.) and the purpose of branding documents. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is relatively concise (two sentences) and front-loaded with the purpose. However, including both French and English makes it slightly longer than necessary for an English-only agent. Still, it's efficient and structured well.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite lacking an output schema, the description enumerates all return fields explicitly. It also provides critical usage context (call before document generation). This makes the tool's behavior fully understood without additional documentation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 100% coverage for the single optional parameter 'broker_code'. The description adds value by stating it comes from find_broker, which helps the agent understand its origin. While not extensive, this context improves usability beyond the schema alone.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool returns broker branding and identity information, listing specific fields. This distinguishes it from siblings like find_broker (which likely searches brokers) and get_products/get_quote (which handle products/quotes).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly instructs to 'ALWAYS call this before generating any document' and provides examples (PDF, PPTX, etc.). This gives clear when-to-use guidance and implies its necessity before other tools in the workflow.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_productsARead-onlyInspect
Catalogue produits assurance / List insurance products with eligibility criteria, coverage details, and indicative pricing. A category is required. Categories: auto, moto, mrh (habitation/home), rc_pro (responsabilité civile/professional liability), protection_juridique (legal), epargne (savings), assurance_vie (life savings), per (retirement savings).
| Name | Required | Description | Default |
|---|---|---|---|
| category | No | Product category filter: auto, moto, mrh, rc_pro, protection_juridique, epargne, assurance_vie, per | |
| broker_code | No | Broker code returned by find_broker. Optional in broker-authenticated mode. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds behavioral context such as the need for a category and the types of information returned. However, it states that category is required while the input schema does not mark it as required, creating a contradiction that could mislead an agent. Annotations are consistent with the read-only nature.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with two sentences covering purpose, required input, and output details. Some redundancy exists (French and English phrasing), but overall it is well-structured and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description explains the return content (eligibility, coverage, pricing). It lacks details on pagination or sorting but covers the essential context for a listing tool. Sibling tools are distinct, and the required category constraint is clear.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The description adds value by explicitly listing the categories and clarifying that broker_code is returned by find_broker and optional in broker-authenticated mode, going beyond the schema's parameter descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists insurance products with eligibility criteria, coverage details, and pricing. It identifies the resource and action, and distinguishes from sibling tools like find_broker, get_broker_info, and get_quote.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly requires a category and lists allowed values, providing clear context. It does not explicitly state when not to use the tool or mention alternatives, but the sibling tools are sufficiently distinct to imply usage boundaries.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_quoteARead-onlyInspect
Tarification assurance en temps réel / Generate real insurance quotes from partner APIs. Devis auto, moto, habitation (MRH), RC Pro, protection juridique, épargne, assurance vie, PER. Returns monthly prices per product and level. No PII stored or returned.
IMPORTANT — birth_date + postal_code are REQUIRED for all products. Use product_data for product-specific information. Call get_products first to see quoteRequirements.guidance for each product — it tells you exactly what to ask the client.
product_data examples by product_type: • auto / moto: {marque, modele, annee, immatriculation, energie, puissance_fiscale, km_annuel, usage, stationnement, date_permis, bonus_malus, sinistres_3ans, formule: tiers/tiers_etendu/tous_risques} • mrh: {type_logement: appartement/maison, statut_occupant: proprietaire/locataire/pno, surface, nb_pieces, etage, annee_construction, alarme, valeur_mobilier} • rc_pro: {activite, code_naf, nb_salaries, ca_annuel} • protection_juridique (pj): {domaine, nb_salaries} • per: {revenus_annuels, tmi, versement_initial, versement_mensuel, profil_risque: prudent/equilibre/dynamique} • assurance_vie: {versement_initial, versement_mensuel, profil_risque, horizon_placement_annees}
| Name | Required | Description | Default |
|---|---|---|---|
| budget | No | Client's monthly budget in euros (e.g. 80). Results sorted by proximity to budget. | |
| gender | No | Gender: M or F | |
| children | No | Children details for family coverage | |
| show_all | No | Return ALL quotes instead of top 5. Use only when client asks for more options. | |
| birth_date | Yes | Client birth date in YYYY-MM-DD format (e.g. '1988-05-15') | |
| has_spouse | No | Whether the client has a spouse/partner to cover | |
| broker_code | No | Broker code returned by find_broker. Optional in broker-authenticated mode. | |
| postal_code | No | French postal code (e.g. '75008', '92150'). Required for all products. | |
| product_data | No | Product-specific data object. Fields depend on product_type — see description above for examples per product. Call get_products first to see quoteRequirements.guidance for the exact fields to collect. | |
| product_type | Yes | Product type: auto, moto, mrh, rc_pro, protection_juridique (pj), epargne, assurance_vie, per | |
| spouse_birth_date | No | Spouse birth date in YYYY-MM-DD format | |
| number_of_children | No | Number of children to cover |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds valuable behavioral info: 'No PII stored or returned.' It also notes it uses partner APIs. This goes beyond the safety profile provided by annotations, though it could mention rate limits or timeouts.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with a clear purpose, important notes, and product examples. It is front-loaded with key information. While lengthy, the examples are necessary for clarity; slight trimming could improve conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (12 params, nested objects, no output schema), the description covers purpose, requirements, product_data structure, and PII handling. It mentions return values ('monthly prices per product and level') and sorting by budget. It lacks output format details but is sufficient for an AI agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description provides extensive product-specific examples for product_data (e.g., auto: marque, modele, etc.) and emphasizes required fields. This adds significant meaning beyond the schema's generic descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool generates real insurance quotes from partner APIs for various product types (auto, moto, mrh, etc.) and returns monthly prices per product and level. It distinguishes itself from sibling tools (find_broker, get_broker_info, get_products) by focusing on quote generation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states that birth_date and postal_code are required for all products, advises using product_data for product-specific information, and recommends calling get_products first to see quoteRequirements.guidance. This provides clear context on prerequisites and how to structure input.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
Discussions
No comments yet. Be the first to start the discussion!