Your customers' next insurance question won't happen in your search box - it'll happen in ChatGPT. We build the ChatGPT Apps, and Claude's equivalent, that let direct-to-consumer insurers and MGAs quote, sell and service customers inside the conversation - with the disclosure, audit trail and complaints handling a regulator expects.
An MCP (Model Context Protocol) app exposes an insurer or MGA's products - quoting and claim service - as a callable app inside ChatGPT, Claude and other AI assistants. OpenAI ships these as ChatGPT Apps (October 2025); Anthropic ships the equivalent as MCP Apps in Claude.ai (January 2026). Both run on the same protocol - built jointly by the two companies as an open spec. The same surface can also serve insurer-to-broker workflows: replacing email as the channel through which a broker submits a quote request and an underwriter responds, without connecting to a rating engine.
Primary: direct-to-consumer in the chat - real quotes and real claim service. Secondary: a broker submission channel that replaces email between brokers and underwriters.
Customers describe what they need in ChatGPT or Claude. Your product responds in the same conversation - bound by the same disclosure and audit obligations as your direct web channel.
Customer describes their need in ChatGPT or Claude. Your app returns a real quote with the disclosures and product summary your regulator requires, and a path to bind.
Identity-verified policyholder asks for a claim update. Your app returns sanitised status, next steps and expected timeframes.
A different shape - and a different audience. Brokers raise submission requests via the same conversational surface to your underwriting team: structured fact-find capture, clarification back-and-forth and the resulting indication or quote, all in one thread instead of a forty-message email chain.
Not connected to your rating engine. Pricing stays with your underwriters. The chat replaces email as the channel for the request, the back-and-forth and the outcome - captured, structured and audit-ready.
Two-week, fixed-price scoping: candidate use case, MCP surface, disclosure model, target architecture.
The MCP-based app, the integrations (to your quoting and policy systems for D2C; to your submission and underwriting case management for broker comms - no rating engine required), and the conversation patterns customers or brokers actually use.
Disclosure blocks, evidence capture for every quote, FSLAA / CoFI-aligned complaints routing, regulator-readable logs.
Submission to the ChatGPT apps directory, the Claude apps surface, and any other MCP-compatible assistants your customers use.
Our strongest practice is brokers, and we've done significant work with insurers and MGAs. We know what a quote and a claim conversation actually has to do.
ChatGPT Apps (October 2025) and Claude MCP Apps (January 2026) both run on the same MCP protocol. We build, ship and operate on that surface as a regular part of our practice - not as an experiment.
Disclosure, audit trail, identity and complaints belong in the MCP server itself. Done at launch, not retrofitted.
FSLAA, FAP, CoFI and the FMA's conduct expectations shape how an insurance app should behave inside an AI chat. We design for that on day one.
Two weeks, fixed price. A board-ready plan for your first MCP app inside ChatGPT and Claude.