How to Use the Brokermint MCP in Vercel AI SDK

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

Install the packages first. Use createMCPClient pointing to your Vinkius endpoint, pull the tools via mcpClient.tools(), and pass them to your text generation function. Remember to call mcpClient.close() when the session ends.

Q: Can Vercel AI SDK handle Brokermint authentication automatically?

Yes, you can configure the authProvider option when setting up your client transport. This passes the secure Vinkius token down to the Brokermint API without exposing credentials to the frontend.

Q: How does streaming prevent timeouts when fetching large Brokermint transaction lists in Vercel AI SDK?

Instead of waiting for listtransactions to resolve completely, Vercel AI SDK streams chunks of the Brokermint payload. Your Edge Functions stay active, and the agent processes the transaction list incrementally.

Q: What React hook works best with this MCP setup?

Use the useChat hook from the SDK. It natively consumes the tool execution states, displaying when the agent is running getaccountinfo or writing a new contact.

Pipe Brokermint transaction data and commission lists directly into React components in real-time 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 Brokermint MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-Time Transaction Feeds in Vercel AI SDK

The `list_transactions` tool lets your AI client pull active real estate deals directly into your UI. By feeding this data directly into the Vercel AI SDK, your application renders active Brokermint files on the screen as the LLM processes the request. This setup means your Vercel AI SDK code can call `get_transaction` inside Edge Functions without hitting timeout limits. The raw Brokermint transaction fields stream straight to your Next.js frontend, letting real estate agents inspect listing statuses and closing dates instantly.

Instant Contact Creation from the Frontend

The `create_contact` tool allows your AI client to instantly build new buyer profiles from raw text. This MCP Server lets your Vercel AI SDK agent parse messy email threads and execute Brokermint `create_contact` or `get_contact` on the fly. When you hook this up with `streamText`, your React components update dynamically to show the newly created Brokermint contact card. The user watches your Vercel AI SDK agent fill out Brokermint contact details in real-time before saving.

Dynamic Commission and User Directories

The `list_commissions` tool retrieves Brokermint brokerage split structures directly for your Vercel AI SDK billing components. Fetching Brokermint splits shouldn't require custom backend endpoints in your Next.js application. By calling `mcpClient.tools()` and passing them to `generateText`, your Vercel AI SDK agent matches Brokermint agents to their respective deal payouts. You get a clean JSON payload of Brokermint commission data ready to render in your React UI.

Setup guide

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

Install the packages first. Use `createMCPClient` pointing to your Vinkius endpoint, pull the tools via `mcpClient.tools()`, and pass them to your text generation function. Remember to call `mcpClient.close()` when the session ends.

Yes, you can configure the `authProvider` option when setting up your client transport. This passes the secure Vinkius token down to the Brokermint API without exposing credentials to the frontend.

Instead of waiting for `list_transactions` to resolve completely, Vercel AI SDK streams chunks of the Brokermint payload. Your Edge Functions stay active, and the agent processes the transaction list incrementally.

Use the `useChat` hook from the SDK. It natively consumes the tool execution states, displaying when the agent is running `get_account_info` or writing a new contact.

Every commission split and payout calculation retrieved via `list_commissions` is processed inside an ephemeral, isolated V8 sandbox. Vinkius never writes this financial data to persistent storage, ensuring broker-agent splits remain completely private.

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