How to Use the CHATFLY MCP in Vercel AI SDK

Q: How do I initialize the CHATFLY MCP Server within Vercel AI SDK?

Install the required packages with npm install ai @ai-sdk/mcp first. Next, call createMCPClient pointing to the Vinkius URL, get the tools using mcpClient.tools(), and pass them to streamText. Always call mcpClient.close() when the session ends to prevent memory leaks.

Q: How does the Vercel AI SDK protect my CHATFLY customer conversation history?

All conversation histories retrieved via getconversationhistory run through a zero-trust V8 sandbox on Vinkius. Your API keys and customer logs never touch a persistent database on our end, keeping your support transcripts isolated and secure.

Build live, streaming customer support UIs in Next.js using CHATFLY tools through 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 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

Stream live CHATFLY bot responses in your Next.js UI

The `send_bot_message` tool streams active support bot replies straight to your Vercel AI SDK application in real-time. Your frontend handles the incoming chunks as they arrive. If a customer asks a complex support question, the agent pulls details via `get_chatbot_details` and streams the custom response without lag.

Real-time knowledge base audits on the frontend

The `list_uploaded_documents` tool pulls your entire knowledge base file list directly into your React frontend. If a doc is missing, the interface can trigger a new training cycle using `trigger_bot_training`. The entire state updates on the fly, keeping your custom support data fresh without page reloads.

Fetch active support history via Vercel AI SDK

The `get_conversation_history` tool fetches raw support logs directly into your Next.js admin dashboard through this MCP Server. The frontend handles the MCP connection lifecycle using `createMCPClient` and streams the chat logs. You get a live-updating dashboard that shows exactly what your CHATFLY bots are telling customers.

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

Install the required packages with `npm install ai @ai-sdk/mcp` first. Next, call `createMCPClient` pointing to the Vinkius URL, get the tools using `mcpClient.tools()`, and pass them to `streamText`. Always call `mcpClient.close()` when the session ends to prevent memory leaks.

Yes, you can stream active conversations directly to your users. By passing the `send_bot_message` tool to your `streamText` function, the model calls the endpoint and streams the response chunks directly to your React or Next.js frontend.

Your frontend agent can trigger training runs on demand. The agent calls `trigger_bot_training` based on user prompts, and you can display the real-time status of the training queue directly in your UI.

Yes, you control this at the agent prompt level or by filtering the output of `list_chatfly_bots`. The SDK executes whatever tools you expose, giving you full control over which bot profiles are visible to your frontend.

All conversation histories retrieved via `get_conversation_history` run through a zero-trust V8 sandbox on Vinkius. Your API keys and customer logs never touch a persistent database on our end, keeping your support transcripts isolated and secure.

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