How to Use the Chatsistant MCP in Vercel AI SDK

Q: How do I use Chatsistant with the Vercel AI SDK to query a bot?

You pass the tools from the MCP client into a streamText call. Your agent can then invoke the querybot tool with a user's question, and the answer will stream directly into your React or Svelte components.

Q: Can I build a dashboard for Chatsistant bots using the Vercel AI SDK?

Yes, that's a core use case. You can use the listbots and listconversations tools to fetch all the data you need. The Vercel AI SDK streams that data right into your UI for a live, responsive dashboard.

Q: What's the setup for connecting Chatsistant to my Vercel AI SDK project?

Install the @ai-sdk/mcp package and use createMCPClient with your Vinkius endpoint URL. Get the tools with mcpClient.tools() and pass them to your generate/stream call. Just remember to use mcpClient.close() when you're done.

Build live customer support dashboards with Chatsistant data streamed directly into your UI using the 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 Chatsistant MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Support Bots in Your UI

This MCP Server gives you the tools to build a full control panel for your white-label assistants right inside your Next.js app. Use `list_bots` to populate a dashboard with every bot you manage. Then, use `get_bot` to drill down into the details for a specific one. When a user interacts with your UI, you can call `query_bot` to get answers from its knowledge base. Because you're using the Vercel AI SDK, the response streams directly into your components character by character. There's no loading spinner, just a live answer appearing on screen.

Live Conversation Monitoring

The `list_conversations` tool lets you pull chat histories for any of your bots. You can build a component that shows new conversations as they happen, filtered by a specific bot if you need. From there, `get_conversation` fetches the full transcript for a single chat. The AI SDK's streaming capability makes this perfect for live agent monitoring screens, where the log appears instantly in your frontend without a page refresh.

Configure Bots via your Vercel AI SDK App

Your app becomes the central hub for managing your entire Chatsistant deployment. Call the `list_data_sources` tool to see what knowledge a bot has. Then, use `add_data_source` to give it new information, all triggered from your own interface. It works the same way for integrations. The `list_webhooks` tool lets you check which external systems are connected to a bot. You can build out a complete settings page for your users, backed by this MCP Server.

Setup guide

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

You pass the tools from the MCP client into a `streamText` call. Your agent can then invoke the `query_bot` tool with a user's question, and the answer will stream directly into your React or Svelte components.

Yes, that's a core use case. You can use the `list_bots` and `list_conversations` tools to fetch all the data you need. The Vercel AI SDK streams that data right into your UI for a live, responsive dashboard.

Install the `@ai-sdk/mcp` package and use `createMCPClient` with your Vinkius endpoint URL. Get the tools with `mcpClient.tools()` and pass them to your generate/stream call. Just remember to use `mcpClient.close()` when you're done.

No, it's for managing the whole Chatsistant platform. You can configure a bot's knowledge base with `add_data_source` or check its integrations with `list_webhooks`. It gives your app operational control.

Vinkius only proxies your requests and never stores your data. Your bot configurations, conversation logs, and data source URLs are passed through ephemeral, sandboxed environments. Your single Vinkius token handles authentication, so your actual Chatsistant credentials are never exposed.

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