How to Use the Flowise MCP in Vercel AI SDK

Q: How do I handle authentication for Flowise inside a Vercel AI SDK app?

You pass your credentials securely using the authProvider config when initializing the MCP client. This ensures the Vercel AI SDK can invoke listcredentials and authenticate your predict calls without exposing raw API keys on the client side.

Q: Can I stream Flowise predictions in Next.js using the Vercel AI SDK?

Yes, you use the predict tool inside streamText to pipe the execution tokens directly to your React components. The Vercel AI SDK handles the edge transport while the Flowise MCP server manages the low-code backend execution.

Q: How do I clean up connection resources after a Flowise run in Vercel AI SDK?

Always call mcpClient.close() once your streaming session finishes. This prevents connection leaks and keeps your serverless functions within their execution limits when querying tools like getchatflow.

Q: Can I filter which Flowise tools are exposed to the frontend?

You use the listtools tool to inspect what is available, then pass only the allowed tool definitions to your frontend model using the MCP client. This keeps your user interface clean and prevents unauthorized execution of backend nodes.

Run low-code Flowise workflows directly inside your Vercel AI SDK application and stream the results to your frontend in real-time.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Flowise MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run and stream predictions with Vercel AI SDK

The `predict` tool executes your low-code Flowise chatflow backend while your Vercel AI SDK frontend streams the output live to your users. You don't make users stare at a blank loading spinner; the moment the Flowise node starts spitting out tokens, they show up in the browser. Setting this up takes minutes. You call `mcpClient.tools()` to grab the tools, pass them straight to `streamText`, and let edge functions handle the heavy lifting.

Discover flows with the Flowise MCP Server

The `list_chatflows` tool queries your active Flowise instance to return all current low-code pipelines. This lets your web application dynamically discover which backend workflows are available and switch between them on the fly based on user input. Your frontend code uses this list to render dropdowns or tabs, giving users direct control over which backend agent they are chatting with. You don't have to hardcode IDs or redeploy your Next.js site every time you build a new agentic flow.

Audit execution history in your React frontend

The `get_history` tool reads past execution sessions directly from your database. Your web client pulls these logs to display historical chat runs to the user, ensuring they never lose context when refreshing the browser tab. Feeding these raw session logs into `generateText` using this MCP tool lets your application summarize past interactions or resume interrupted conversations. You get clean JSON arrays back, which map directly to the message arrays expected by the UI.

Setup guide

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

You pass your credentials securely using the `authProvider` config when initializing the MCP client. This ensures the Vercel AI SDK can invoke `list_credentials` and authenticate your `predict` calls without exposing raw API keys on the client side.

Yes, you use the `predict` tool inside `streamText` to pipe the execution tokens directly to your React components. The Vercel AI SDK handles the edge transport while the Flowise MCP server manages the low-code backend execution.

Always call `mcpClient.close()` once your streaming session finishes. This prevents connection leaks and keeps your serverless functions within their execution limits when querying tools like `get_chatflow`.

You use the `list_tools` tool to inspect what is available, then pass only the allowed tool definitions to your frontend model using the MCP client. This keeps your user interface clean and prevents unauthorized execution of backend nodes.

All communications run through an ephemeral V8 sandbox on Vinkius, meaning your Flowise API keys and execution logs are never cached or logged on our infrastructure. The `list_credentials` and `get_history` tools execute in isolated memory, passing data directly to your Vercel AI SDK serverless route without disk persistence.

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