How to Use the ChatGen MCP in Vercel AI SDK

Q: How does the Vercel AI SDK connect to the ChatGen MCP Server?

You'll use the createMCPClient function from @ai-sdk/mcp. Just pass your Vinkius transport URL, and then call mcpClient.tools() to get the ChatGen tools. You can then provide these tools to generateText or streamText.

Q: Can I stream ChatGen conversation logs with the Vercel AI SDK?

Yes. Your agent can call the listconversations tool. The Vercel AI SDK will stream the conversation data as it arrives, letting you render it live in your application's UI.

Q: Is it possible to build a real-time lead dashboard for ChatGen using the Vercel AI SDK?

That's a perfect use case. Your agent uses the listleads and getleaddetails tools to get the data. The AI SDK's streaming features mean you can build a UI where leads pop into the dashboard the instant your agent gets them.

Q: What's the best way to list all my active bots?

Have your agent call the listbots tool. The server will return a complete list of your ChatGen bots, which you can then display or process within your application.

Build UIs that show ChatGen working in real time. Stream bot activity and lead data directly into your Vercel AI SDK app.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ChatGen MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Chatbots, Live in Your UI

This MCP Server gives your agent direct control over your ChatGen bots. You can `create_bot`, `update_bot`, or `delete_bot` right from your own interface. The agent calls the tool, and the operation happens instantly. Because you're using the Vercel AI SDK, you can build a UI that reflects these changes without a page refresh. When your agent calls `list_bots`, you can stream the results directly into a React component, showing a live-updating list of all your active chatbots.

Stream ChatGen Leads with the Vercel AI SDK

Get a live feed of the leads your chatbots are capturing. Your agent can use the `list_leads` tool to get a constant flow of new prospects. From there, it can use `get_lead_details` to pull specific information for any single lead. This isn't just about fetching data after the fact. The Vercel AI SDK lets you stream this information directly into your UI. You can build a dashboard where new leads appear the moment your agent finds them, giving your sales team a real-time view of the pipeline.

Build Custom Support Dashboards

Stop using a generic admin panel. This MCP Server provides all the backend operations you need to build your own custom interface for managing ChatGen. Your agent can pull bot stats, conversation histories, and team structures on command. Combine tools like `get_bot`, `list_conversations`, and `list_teams` to create a single view of your entire ChatGen operation. Since the AI SDK streams tool results, your custom dashboard will feel faster and more responsive than a standard web app.

Setup guide

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

You'll use the `createMCPClient` function from `@ai-sdk/mcp`. Just pass your Vinkius transport URL, and then call `mcpClient.tools()` to get the ChatGen tools. You can then provide these tools to `generateText` or `streamText`.

Yes. Your agent can call the `list_conversations` tool. The Vercel AI SDK will stream the conversation data as it arrives, letting you render it live in your application's UI.

That's a perfect use case. Your agent uses the `list_leads` and `get_lead_details` tools to get the data. The AI SDK's streaming features mean you can build a UI where leads pop into the dashboard the instant your agent gets them.

Have your agent call the `list_bots` tool. The server will return a complete list of your ChatGen bots, which you can then display or process within your application.

Your connection is secured by a unique endpoint token. The server only handles your ChatGen bot configurations, conversation text, and lead details. Everything runs inside a V8 Isolate sandbox, meaning each request is fully isolated and the environment is destroyed afterward.

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