How to Use the Kustomer MCP in Vercel AI SDK

Q: How do I connect Kustomer to the Vercel AI SDK?

Install @ai-sdk/mcp and initialize your client with createMCPClient. Point the HTTP transport to your Vercel endpoint. Call mcpClient.tools() and pass them straight into your streamText function.

Q: Can Vercel AI SDK stream Kustomer timeline searches?

Yes. When the model invokes searchkustomertimeline, the SDK streams the tool call execution back to the client. Your React UI updates as the results arrive over the wire.

Q: Do I need to close the MCP connection?

Always call mcpClient.close() when your Edge function finishes. Leaving connections hanging will bleed resources and break your serverless deployment limits.

Stream live support data straight to your React frontend. Vercel AI SDK connects your UI to Kustomer instantly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kustomer MCP to Vercel AI SDK

Create your Vinkius account to connect Kustomer 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 Kustomer with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build live dashboards with this MCP Server.

Connect this MCP Server to your Edge functions to pull active queues with `list_support_conversations`. You don't want users staring at loading spinners while your app fetches ticket histories. Your agent streams the active queue straight into your Next.js frontend as fast as the API returns it. The real magic happens when users click a specific thread. Your application fires off `get_conversation_details` and `list_conversation_messages` behind the scenes. The text renders piece by piece as the LLM processes it. It feels instant because it is.

Render customer profiles without the wait.

Your system calls `get_customer_profile` the moment a chat opens to give reps immediate context. Support reps need context before they type a single word. Give them a custom UI that automatically pulls up the user's background without making them click through five different tabs. Instead of building complex REST wrappers, you just pass these tools to `streamText`. If you need to dig deeper, `search_kustomer_timeline` pulls the exact interactions you want. The agent formats the data and pushes it to your Svelte components live.

Map custom data objects on the fly.

Grab the exact schema your team built using `list_data_klasses` instead of hardcoding custom fields. Every enterprise support team uses custom fields. You can't hardcode them into your frontend without breaking things every time a manager adds a new tag. The LLM reads the custom classes and understands exactly what data structure to expect. When it pulls metrics via `list_kustomer_customers`, it formats the payload perfectly for your Vue application. No manual mapping required.

Setup guide

Set up Kustomer 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 Kustomer 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 Kustomer 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 Kustomer. 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 Kustomer 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 Kustomer MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and initialize your client with `createMCPClient`. Point the HTTP transport to your Vercel endpoint. Call `mcpClient.tools()` and pass them straight into your `streamText` function.

Yes. When the model invokes `search_kustomer_timeline`, the SDK streams the tool call execution back to the client. Your React UI updates as the results arrive over the wire.

Always call `mcpClient.close()` when your Edge function finishes. Leaving connections hanging will bleed resources and break your serverless deployment limits.

You handle that in your system prompt. Tell the agent to run `list_support_queues` and only process tickets from specific departments like Billing or Tech Support.

This server processes raw support messages, customer IDs, and agent names. The V8 Isolate Sandbox destroys the execution environment the second your HTTP request finishes. Nothing persists in memory, keeping your PII strictly ephemeral.

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