How to Use the Sobot MCP in Vercel AI SDK

Q: How does Sobot integrate with ai-sdk for real-time data?

The ai-sdk handles streaming responses from the MCP Server directly into your UI. This means when you call a tool like getticketdetails, the data appears on the screen progressively, giving the user live feedback instead of waiting for one big payload.

Q: What type of data does Sobot touch regarding privacy?

This MCP Server touches customer account information via listusers and message content through listchathistory. Always handle this user data with strict access controls within your client.

Build Live Data Streams with the ai-sdk: Show users exactly how Sobot handles support requests.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Sobot MCP to Vercel AI SDK

Create your Vinkius account to connect Sobot to Vercel AI SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Sobot with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Live Agent Status Updates

Use `get_agent_status` to show your user what's happening right now. This lets the end-user see if an agent is online or busy, updating the UI in real time as data streams into the frontend. It’s perfect for showing a customer exactly when they can expect help. You don't have to wait for a loading spinner; the status updates live as your client processes the MCP Server response.

Fetch Full Ticket Histories

Need context? Call `list_chat_history` and get every message exchanged during a support session. This data streams directly into your React component, building out the chat window piece by piece as it arrives. Your agent’s view won't feel like a static dump of text; it will look dynamic, making the entire interaction feel immediate and live for both the user and the developer.

View User Records

Use `list_users` to get a list of all customer accounts. This is critical data that needs to appear fast in your UI, so seeing it stream directly from the MCP Server prevents any noticeable lag. Instead of waiting for an API call to resolve and dump a massive JSON object, you display the user record as it’s built out on the wire.

Setup guide

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

The `ai-sdk` handles streaming responses from the MCP Server directly into your UI. This means when you call a tool like `get_ticket_details`, the data appears on the screen progressively, giving the user live feedback instead of waiting for one big payload.

This MCP Server touches customer account information via `list_users` and message content through `list_chat_history`. Always handle this user data with strict access controls within your client.

Absolutely. The MCP Server supports streaming output, which means it works perfectly for `ai-sdk`. You can call tools like `list_knowledge` and display the resulting article list piece by piece in your frontend.

While streaming is powerful, remember that calling too many complex tools rapidly can still tax your client's network. Keep an eye on how quickly your front end renders data from calls like `list_tickets`.

Yes, it’s designed to work with streaming protocols. You can trust that calling tools will deliver results in chunks, which is exactly what `ai-sdk` is built to consume.

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