How to Use the ChatBot.com MCP in Vercel AI SDK

Q: How do I connect ChatBot.com to Vercel AI SDK?

Install @ai-sdk/mcp and initialize createMCPClient. Pass the Vinkius endpoint URL and call mcpClient.tools() to inject them into streamText.

Q: Can the Vercel AI SDK stream ChatBot.com user data?

Yes. When the agent calls getchatbotuserdetails, the resulting JSON streams chunk-by-chunk to your React or Svelte UI.

Q: How do I close the ChatBot.com connection in Vercel AI SDK?

Always invoke mcpClient.close() after your generation finishes. This prevents memory leaks in long-running serverless environments.

Build live conversational management interfaces. Connect ChatBot.com to your Vercel AI SDK frontends and stream bot analytics straight to users.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ChatBot.com MCP to Vercel AI SDK

Create your Vinkius account to connect ChatBot.com 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 ChatBot.com with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream ChatBot.com Stories via MCP Server

Pulling bot workflow data requires the `list_chatbot_stories` and `get_story_details` tools. You pass these into your `streamText` function, and the Vercel AI SDK handles the transport layer. Your React frontend receives the story structures and renders them instantly without waiting for the entire payload to resolve. Getting interaction data works exactly the same way. When a user requests conversation history, your agent calls `list_story_interactions`. The results stream directly into your UI components. End users watch the chat logs appear line by line instead of staring at a blank loading screen.

Live User Data in the UI

Extracting specific customer profiles relies on the `get_chatbot_user_details` and `list_chatbot_users` tools. This setup lets your application pull demographic and behavioral data from ChatBot.com on demand. The MCP Server acts as a fast bridge between the raw API and your edge functions. Pushing this data to Svelte or Vue happens instantly. You can build internal dashboards where support agents ask for a specific user's chat history, and the LLM retrieves it live. No custom polling logic or background workers required.

Expose Training Data to the Frontend

Identifying failed bot matches requires the `list_training_data` tool. Your application pulls unrecognized phrases straight from ChatBot.com into the browser. The AI agent processes these missed utterances and suggests new intents right in your custom interface. Managing integrations is handled by `list_chatbot_webhooks`. You can display active webhook connections alongside the training data. Developers get a full view of bot health and routing rules directly in their Next.js application.

Setup guide

Set up ChatBot.com 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 ChatBot.com 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 ChatBot.com 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 ChatBot. 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 ChatBot.com 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 ChatBot.com MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and initialize `createMCPClient`. Pass the Vinkius endpoint URL and call `mcpClient.tools()` to inject them into `streamText`.

Yes. When the agent calls `get_chatbot_user_details`, the resulting JSON streams chunk-by-chunk to your React or Svelte UI.

It runs perfectly on the Edge. The HTTP transport layer adds minimal overhead, keeping your Vercel AI SDK responses fast.

Always invoke `mcpClient.close()` after your generation finishes. This prevents memory leaks in long-running serverless environments.

Vinkius executes every request inside a V8 Isolate sandbox. Your raw chat transcripts and unrecognized phrases from `list_training_data` never touch disk storage. The environment destroys itself immediately after returning the payload.

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