How to Use the HiFlow MCP in Vercel AI SDK

Q: How do I connect HiFlow to Vercel AI SDK?

Install @ai-sdk/mcp and ai via npm. Use createMCPClient to build your MCP connection with the HTTP transport URL. Pass the resulting tool array to your streamText function. Always call mcpClient.close() when the session ends.

Q: Can I stream HiFlow timesheets into my Next.js app with Vercel AI SDK?

Yes. You pass the listtimesheets tool to your agent. As the server returns the timesheet entries, Vercel AI SDK streams the JSON directly to your React components for immediate rendering.

Q: Does the HiFlow Vercel AI SDK integration support OAuth?

It does. You configure the authProvider in your MCP client setup. This ensures your users only see the estimates and jobs they actually have permission to view.

Connect HiFlow to Vercel AI SDK and stream live billing and customer data straight into your React frontends.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HiFlow MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Invoices with Vercel AI SDK

The `list_invoices` and `get_invoice` tools pull billing records directly into your application state. Vercel AI SDK handles the streaming response, meaning your users watch the invoice details render on screen line by line instead of staring at a loading spinner. You can build a dashboard where the AI client fetches a specific record using `get_job` and immediately formats it into your Next.js UI components. This cuts out the usual middleware layers and drops raw workflow data right where the user needs it.

Live Customer Activity Feeds

The `get_activity` tool surfaces what is happening across your business right now. Tie this into a generative UI component, and your support team gets an instantly updating view of recent customer interactions. If they need more context, the agent can automatically trigger `get_customer` to pull the full profile. Your frontend stays fast because the MCP Server handles the actual data extraction securely in the background.

Real-Time Estimate Generation

Generating quotes usually requires jumping between tabs, but the `list_estimates` and `get_estimate` tools bring that data into your chat interface. Your users ask for a project quote, and the agent retrieves the exact figures. Because you are using an edge-compatible setup, these requests resolve fast. You just pass the tools to `streamText`, and the application handles the rest of the heavy lifting.

Setup guide

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

Install `@ai-sdk/mcp` and `ai` via npm. Use `createMCPClient` to build your MCP connection with the HTTP transport URL. Pass the resulting tool array to your `streamText` function. Always call `mcpClient.close()` when the session ends.

Yes. You pass the `list_timesheets` tool to your agent. As the server returns the timesheet entries, Vercel AI SDK streams the JSON directly to your React components for immediate rendering.

It does. You configure the `authProvider` in your MCP client setup. This ensures your users only see the estimates and jobs they actually have permission to view.

The tool execution returns an error state to the agent. You can catch this in your application logic and render a fallback UI component instead of breaking the entire chat session.

Vinkius runs the server inside a V8 Isolate Sandbox. When your agent pulls data via `get_customer` or `list_invoices`, the connection is ephemeral and strictly isolated. The network drops the sandbox the moment your request finishes, leaving zero residual data behind.

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