How to Use the ChatFly MCP in Vercel AI SDK

Q: How do I configure ChatFly with the Vercel AI SDK?

You install the @ai-sdk/mcp package and set up an HTTP client pointing to the Vinkius endpoint. From there, pass the tools directly into the SDK's text generation functions to let your agent call createbot or chat on demand.

Q: Can Vercel AI SDK handle multiple ChatFly bots at once?

Yes. Your code can call listbots to fetch the complete registry of active agents, then let the user select which one to modify via updatebot in the UI.

Q: How does token streaming work with the chat tool?

The chat tool executes on the Vinkius sandbox, and the resulting text chunks pipe through the SDK's streaming transport. Your UI displays the bot's response character by character as it processes.

Q: How secure is my data source content when using this MCP Server?

The text files and customer interactions you feed into uploaddatasource are processed inside isolated V8 sandboxes on Vinkius. We never store raw training documents on our hosting layer, and all API calls use short-lived, single-purpose tokens.

Build live-streaming chatbot dashboards in Next.js that spin up and feed customer support bots using 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 ChatFly MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time bot deployment with Vercel AI SDK

Your Next.js app can run the `create_bot` tool to instantly spin up customer support agents without making users wait for slow API responses. Your users see the welcome message and initial parameters render on their screen without staring at a blank loading spinner. You hook the tool outputs right into the React tree so the live state updates as soon as the bot exists.

Instant knowledge base feeding

The `upload_data_source` tool binds training documents directly to a specific bot ID while streaming the ingestion status to your frontend. You can list what's already active by calling `list_data_sources` in the background. The SDK handles the raw data stream so your UI updates the file list dynamically as training finishes.

Interactive diagnostic testing

Testing a live agent becomes incredibly fast when you feed user prompts into the `chat` tool inside a custom playground. By calling `get_bot` to load the current config and piping it to the chat interface, you build a side-by-side testing sandbox. It feels like a local app because the token-by-token response streams directly into your custom chat component.

Setup guide

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

You install the `@ai-sdk/mcp` package and set up an HTTP client pointing to the Vinkius endpoint. From there, pass the tools directly into the SDK's text generation functions to let your agent call `create_bot` or `chat` on demand.

Yes. Your code can call `list_bots` to fetch the complete registry of active agents, then let the user select which one to modify via `update_bot` in the UI.

No, you don't need a local sync database. You can query the current state live using `get_bot` and let the Vercel AI SDK render the fresh configuration directly to the frontend.

The `chat` tool executes on the Vinkius sandbox, and the resulting text chunks pipe through the SDK's streaming transport. Your UI displays the bot's response character by character as it processes.

The text files and customer interactions you feed into `upload_data_source` are processed inside isolated V8 sandboxes on Vinkius. We never store raw training documents on our hosting layer, and all API calls use short-lived, single-purpose tokens.

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