How to Use the HubSpot MCP in Vercel AI SDK

Q: How do I connect the HubSpot MCP Server to Vercel AI SDK?

Use createMCPClient with an HTTP transport URL pointing to your Vinkius endpoint. Then pass mcpClient.tools() into your streamText function. Always remember to call mcpClient.close() when the session ends.

Q: Can Vercel AI SDK stream HubSpot deal updates in real-time?

Yes. As the agent retrieves data via the getdealdetails tool, the SDK pushes those chunks to your frontend instantly. Your users see the deal amounts appear as the LLM processes them.

Q: Does the Vercel AI SDK support OAuth for HubSpot authentication?

It does. You can configure the authProvider in your setup to handle secure token exchanges. This keeps your users from having to paste raw API keys into your app.

Build live CRM dashboards where Vercel AI SDK streams HubSpot data directly into your React frontend.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HubSpot MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream CRM records via Vercel AI SDK

This MCP Server connects your edge functions straight to your sales database. You ask for an account overview. Your agent calls `list_deals` and `get_company_info` to pull the exact figures. You don't have to wait for the entire API response to finish. The SDK streams those deal stages directly into your React UI as they arrive. Users see the data instantly. Deal amounts appear before the final token even generates.

Build interactive contact management

The `create_contact` tool on this MCP Server gives your frontend the ability to generate records on the fly. Your application needs to let users update leads without leaving the page. A sales rep types a name into your custom chat interface. The system finds the match, grabs the details with `get_contact_details`, and renders a live interactive card right in the browser. Contact profiles load without a page refresh.

Map complex associations instantly

The `link_crm_objects` tool lets your MCP client handle complex database relationships automatically. Managing associations between people and businesses gets messy fast. Let's fix that. You build a workflow that reads an incoming email and ties the sender to an existing account. If the account is missing, the agent checks `get_object_schema` to format the new entry correctly before saving it. No more rejected API payloads.

Setup guide

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

Use `createMCPClient` with an HTTP transport URL pointing to your Vinkius endpoint. Then pass `mcpClient.tools()` into your `streamText` function. Always remember to call `mcpClient.close()` when the session ends.

Yes. As the agent retrieves data via the `get_deal_details` tool, the SDK pushes those chunks to your frontend instantly. Your users see the deal amounts appear as the LLM processes them.

It does. You can configure the `authProvider` in your setup to handle secure token exchanges. This keeps your users from having to paste raw API keys into your app.

The SDK catches the error and surfaces it in the stream's error boundary. You can render a fallback UI while the agent decides whether to retry the request.

Your application pulls sensitive contact details and deal amounts through an ephemeral V8 Isolate Sandbox. Vinkius tears down the environment the moment your session concludes, leaving no persistent cache of your customer records.

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