How to Use the Guidewire ClaimCenter MCP in Vercel AI SDK

Q: How do I query Guidewire ClaimCenter claims with the Vercel AI SDK?

Use the listclaimcenterclaims tool inside your generateText or streamText function. The SDK calls our MCP Server over a secure HTTP connection, retrieving active files based on your search filters.

Q: Can I stream Guidewire ClaimCenter exposures using Vercel AI SDK?

Yes, you can feed listclaimexposures to your agent to stream financial reserves and coverages live. The data streams directly into your UI components, showing the financial breakdown without page refreshes.

Q: How does Vercel AI SDK handle Guidewire ClaimCenter document lists?

The SDK executes listclaimdocuments to fetch the file metadata for a specific claim. It returns a structured array of document names and upload dates that you can render instantly in your React or Next.js layout.

Q: What is the setup process for this integration?

Install the @ai-sdk/mcp package and create an HTTP transport client pointing to the Vinkius endpoint. Pass the tools directly to your model call, and remember to close the client connection when the execution finishes.

Feed live Guidewire ClaimCenter file details and adjuster updates straight to your Next.js frontend with Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Guidewire ClaimCenter MCP to Vercel AI SDK

Create your Vinkius account to connect Guidewire ClaimCenter to Vercel AI SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Guidewire ClaimCenter with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live claim tracking with Vercel AI SDK

The `list_claimcenter_claims` tool feeds active insurance files directly into your streaming React components. This tool lets your AI client find specific files instantly, bypassing the sluggish legacy database queries that slow down your claims team. Your frontend renders the incoming data block-by-block instead of showing a blank loading spinner. When an adjuster clicks a file, the SDK calls `get_claim_details` to stream the specific coverage details and policy boundaries straight to their dashboard.

Track open exposures and active tasks

The `list_claim_exposures` tool identifies financial liabilities and coverage impacts on open insurance files. By feeding this MCP tool to your Vercel AI SDK setup, you let your agent analyze outstanding reserves and present them in a live dashboard. The agent then runs `list_claim_activities` to show which tasks are bottlenecking the file. Adjusters see their active task lists update dynamically as the model processes the files on Edge Functions.

Access internal notes and contact directories

The `list_claim_notes` tool retrieves historical adjuster commentary and file updates from your ClaimCenter database. Your AI client uses this MCP server to read these notes and summarize complex claim histories for junior adjusters without manual copy-pasting. At the same time, the `list_claim_contacts` tool pulls contact details for claimants, vendors, and medical providers. This lets your frontend build interactive communication hubs where adjusters can click to contact parties directly from the streamed summary.

Setup guide

Set up Guidewire ClaimCenter MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Guidewire ClaimCenter tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Guidewire ClaimCenter transactions",
});

console.log(text);
await mcpClient.close();

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Guidewire ClaimCenter. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Guidewire ClaimCenter now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Guidewire ClaimCenter MCP in Vercel AI SDK

Use the `list_claimcenter_claims` tool inside your `generateText` or `streamText` function. The SDK calls our MCP Server over a secure HTTP connection, retrieving active files based on your search filters.

Yes, you can feed `list_claim_exposures` to your agent to stream financial reserves and coverages live. The data streams directly into your UI components, showing the financial breakdown without page refreshes.

The SDK executes `list_claim_documents` to fetch the file metadata for a specific claim. It returns a structured array of document names and upload dates that you can render instantly in your React or Next.js layout.

Install the `@ai-sdk/mcp` package and create an HTTP transport client pointing to the Vinkius endpoint. Pass the tools directly to your model call, and remember to close the client connection when the execution finishes.

All communication with Guidewire ClaimCenter runs inside an ephemeral, zero-trust V8 sandbox on Vinkius. We never store your claims data, adjuster notes, or contact info; we simply pass the encrypted API requests through to your core database.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript