How to Use the Ask Kodiak MCP in Vercel AI SDK

Q: How do I initialize Ask Kodiak with the Vercel AI SDK?

Install the required packages via npm, then use createMCPClient pointing to your Vinkius endpoint. Pass the tools directly to streamText and ensure you call mcpClient.close() when the session ends to free up resources.

Q: How does the Vercel AI SDK handle OAuth for Ask Kodiak?

The SDK uses the authProvider configuration inside your MCP client setup. This securely passes user credentials down to the getaccountcheck tool to verify the active session before querying any carrier data.

Q: How do I handle multi-carrier queries with this MCP Server?

You map the listcompanies tool output to parallel model calls. The Vercel AI SDK streams the responses from multiple carriers simultaneously, letting you compare appetites on a single dashboard.

Pipe commercial insurance appetite data directly into your frontend using 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 Ask Kodiak MCP to Vercel AI SDK

Create your Vinkius account to connect Ask Kodiak 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 Ask Kodiak with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live carrier appetite feeds with Vercel AI SDK

The `get_product` tool lets your frontend application fetch exact appetite criteria and underwriting guidelines directly from insurance carriers. By passing these tool definitions to `streamText`, your user interface renders specific appetite rules step-by-step as the model evaluates them. You don't have to make users wait for a massive payload to download. The Vercel AI SDK handles the asynchronous chunking, rendering carrier requirements on screen the moment they resolve.

Instant classification lookups using this MCP Server

The `suggest_naics` tool queries the Ask Kodiak classification engine to find correct codes based on plain-text business descriptions. Your application pairs this with `list_classifications` to map business activities to carrier-specific codes without manual searching. Running this on edge functions keeps latency low. Your UI updates the classification dropdowns dynamically while the user types, eliminating traditional form friction.

Live commercial insurance product search

The `list_products` tool searches the market for commercial insurance products matching your client's risk profile. Your frontend displays these plans alongside specific carrier details retrieved via `list_companies` and `get_company_products`. Users see matches populate their dashboard instantly. Because the MCP client handles the underlying API calls, your UI code stays clean and focused entirely on layout.

Setup guide

Set up Ask Kodiak 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 Ask Kodiak 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 Ask Kodiak 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 Ask Kodiak. 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 Ask Kodiak 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 Ask Kodiak MCP in Vercel AI SDK

Install the required packages via npm, then use `createMCPClient` pointing to your Vinkius endpoint. Pass the tools directly to `streamText` and ensure you call `mcpClient.close()` when the session ends to free up resources.

Yes. The Vinkius MCP client is fully compatible with Edge runtimes, allowing your application to fetch carrier products using `list_products` without cold-start delays.

The SDK uses the `authProvider` configuration inside your MCP client setup. This securely passes user credentials down to the `get_account_check` tool to verify the active session before querying any carrier data.

You map the `list_companies` tool output to parallel model calls. The Vercel AI SDK streams the responses from multiple carriers simultaneously, letting you compare appetites on a single dashboard.

Your queries, classification searches, and NAICS codes are processed inside isolated, ephemeral V8 sandboxes. No raw insurance data or carrier appetite lookups are stored on the Vinkius platform after the request lifecycle completes.

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