How to Use the HubSpot CRM MCP in Vercel AI SDK

Q: Can I use Vercel AI SDK to update custom HubSpot CRM properties?

Yes, you can pass custom fields directly through the hsupdatecontact and hsupdatecompany tools. The Vercel AI SDK maps these parameters from your schema definitions. This allows your agent to modify custom fields just like standard ones.

Q: How do I close the connection once the agent finishes?

You must call mcpClient.close() at the end of your execution block. This prevents connection leaks in your serverless environments. It is a critical step for maintaining clean resource usage on Vercel.

Feed HubSpot CRM customer data directly into your 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 HubSpot CRM MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream HubSpot CRM updates to Vercel AI SDK frontends

Stop making users wait for a spinning loader when they look up custom properties. Your Next.js frontend can now display live contact details as they arrive from the HubSpot API. By hooking the Vercel AI SDK up to this MCP server, your agent calls `hs_get_contact` and immediately pushes the raw JSON payload straight into your UI components. This setup works natively inside Edge Functions without adding cold-start latency. When a user asks to modify a record, the agent runs `hs_update_contact` on the fly. The UI updates instantly, letting your users see the changes happen right before their eyes instead of staring at a blank screen.

Clean search and association mapping

Finding the right company shouldn't require a complex multi-step form. Let your agent handle the lookup by passing natural language queries directly to `hs_search_companies` to retrieve matching entities. Once the correct company is found, the agent can immediately query `hs_get_associations` to pull all linked contacts. This gives your Next.js application a clean way to display account hierarchies without writing custom backend glue code. The underlying MCP client handles the transport layer, so you can focus on building clean React views that render these complex relationships.

Instant task and activity logging

Keep your sales pipeline updated without leaving your application's chat interface. Your agent can immediately write structured follow-ups by invoking `hs_create_task` with specific priorities and due dates. There is no need to manually log in to the HubSpot portal just to set a reminder. For richer context, the agent can write HTML-formatted records directly to the timeline using `hs_create_note`. This means every conversation, meeting summary, or action item gets logged to the correct contact record without any manual copy-pasting.

Setup guide

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

Vinkius manages the API connection pools directly, so your frontend doesn't hit HubSpot rate limits during peak usage. The Vercel AI SDK calls the managed MCP Server, which queues requests and handles retries automatically. This keeps your Edge Functions fast and compliant.

Yes, you can pass custom fields directly through the `hs_update_contact` and `hs_update_company` tools. The Vercel AI SDK maps these parameters from your schema definitions. This allows your agent to modify custom fields just like standard ones.

Yes, tool execution results feed directly into your stream. When the agent calls `hs_search_contacts`, the resulting contact records stream back to your React frontend in real-time. You don't have to wait for the entire search payload to resolve before rendering.

You must call `mcpClient.close()` at the end of your execution block. This prevents connection leaks in your serverless environments. It is a critical step for maintaining clean resource usage on Vercel.

Your contact details, interaction notes, and tasks never touch external persistent storage. Vinkius runs the server in an ephemeral V8 sandbox that isolates your API keys and active sessions. All payloads are encrypted in transit and discarded immediately after the tool execution completes.

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