Insurance Claims Assistant

An MCP server for automated car insurance claim processing, built with TypeScript and the Anthropic Claude API.

I built this after a year working on Guidewire ClaimCenter at AXA France, where I integrated the EDI broker flows (506/508/509) for automated claim opening and modification. The business logic here mirrors what I dealt with there — entity extraction, severity triage, broker notifications — but implemented with LLMs instead of static rules.

The core of it is a two-model validation pipeline: a fast model classifies, a stronger model reviews and can overrule it before anything ships.

What it does

Three tools, chained together:

    ↓  analyze_claim_report
Structured ClaimData
    ↓  classify_claim_severity
Severity + judge verdict
    ↓  generate_broker_notification
Formal broker notification

The judge

Classification runs through two models.

Claude Haiku takes the structured claim and returns a severity plus a confidence score and its reasoning. Claude Sonnet then receives the same claim data alongside Haiku's answer, and returns a verdict:

{
  "approved": false,
  "feedback": "Injuries confirmed in the report — AUTO_PROCESS is not applicable",
  "finalSeverity": "URGENT_ESCALATION"
}

Sonnet doesn't ask Haiku to retry. It overrides directly, and finalSeverity is what the pipeline uses downstream. The judge always has the last word.

The reason this pattern is here and not somewhere cheaper: in claims processing, a misclassification isn't a cosmetic error. An URGENT_ESCALATION claim with injuries routed to AUTO_PROCESS means someone waits longer for assistance. Haiku is cheap enough to run on every claim; Sonnet costs more but only runs once, as a gate.

analyze_claim_report

Takes raw accident report text and returns structured JSON: vehicles, parties, damages, circumstances, witnesses.

Uses an Agent Skill pattern — the extraction prompt lives in its own module (skills/claim-extraction.skill.ts) rather than being inlined in the tool.

classify_claim_severity

Classifies a claim as AUTO_PROCESS, REVIEW_NEEDED, or URGENT_ESCALATION.

generate_broker_notification

Generates a formal notification letter for the broker, with the required actions based on the severity classification.

This one sends MCP progress notifications (1/3, 2/3, 3/3) so the client can display real-time status.

Architecture

├── index.ts                       MCP server, tool registration
├── tools/
│   ├── analyze-claim.ts
│   ├── classify-claim.ts
│   └── generate-notification.ts
├── skills/
│   └── claim-extraction.skill.ts  Reusable prompt template
├── judge/
│   └── classification-judge.ts    Sonnet validates Haiku
├── utils/
│   ├── anthropic-client.ts        Shared SDK instance + model config
│   ├── logger.ts                  stderr logging
│   └── progress.ts                Progress notification helper
└── types/
    └── claim.types.ts

A few decisions worth explaining

Logging goes to stderr, not stdout. MCP servers using stdio transport reserve stdout for JSON-RPC messages. A stray console.log corrupts the protocol and the client drops the connection. Everything logs to stderr instead.

Haiku everywhere except the judge. Extraction, classification, and notification generation all run on Haiku. Sonnet only runs as the validator. On a real claim volume, that cost difference matters.

Progress notifications are optional. The sendProgressFn parameter is optional so the tool still works with clients that don't support progress updates. No client should crash because it didn't send a progress token.

Zod for input validation. The MCP SDK uses Zod schemas to validate tool inputs at the server boundary, before any business logic runs. It also gives typed handler arguments for free.

Setup

Requires Node.js 18+ and an Anthropic API key.

git clone https://github.com/youssefmkb/insurance-claims-assistant
cd insurance-claims-assistant
npm install
cp .env.example .env    # add your API key
npm run build

Run the server:

node dist/index.js

Test it with MCP Inspector:

npx @modelcontextprotocol/inspector node dist/index.js

Screenshots

Tools exposed by the server:

Entity extraction from a raw accident report:

Classification with the judge verdict:

Broker notification, with progress updates visible bottom right:

Stack

Node.js, TypeScript, @modelcontextprotocol/sdk v4, Anthropic SDK (Haiku + Sonnet), Zod, stdio transport.

V2 ideas

Things I'd add if this went further:

• Actual email delivery — right now the notification is generated but not sent. Hooking up SendGrid or Nodemailer would close the loop.
• Persistence — claims are stateless today. A database would let you track a claim across its lifecycle instead of processing each call in isolation.
• MCP sampling — let the server request completions from the client's model rather than calling the API directly.
• Remote transport — currently stdio only. Streamable HTTP would make it deployable.

Author

Youssef Mokhbi — github.com/youssefmkb · LinkedIn