How to Use the GoHighLevel MCP in Vercel AI SDK

Q: How do I connect GoHighLevel to my Vercel AI SDK app?

Install @ai-sdk/mcp and initialize the client using the Vinkius URL. This connects your application to the MCP Server instantly. Pass the tools from mcpClient.tools() directly into generateText or streamText, and remember to call mcpClient.close() when you are done so you don't leak memory.

Q: Can a Vercel AI SDK agent schedule appointments in GoHighLevel?

Yes. The agent uses listcalendars to fetch available booking slots from your CRM. It can then present these slots to the user in the chat UI and trigger a contact update to book the slot.

Feed live GoHighLevel pipeline updates and contact records directly into your Next.js frontend with the 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 GoHighLevel MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live GoHighLevel pipeline updates to your Vercel AI SDK UI

The `list_pipelines` tool lets your agent pull active sales stages directly into your React components without laggy page reloads. Your users see deals move across stages in real-time as the Vercel AI SDK streams the raw JSON payload straight into your UI components. This MCP Server connection bypasses the typical loading spinners by using Edge-compatible streaming. By combining `list_opportunities` with `get_contact`, your application renders updated deal sizes and contact profiles the second the agent fetches them.

Instant lead capture and contact creation

The `create_contact` tool handles user registration by sending form submissions straight to your CRM from any Edge Function. Your agent processes incoming chat inputs, extracts lead details, and updates GoHighLevel instantly. You don't need heavy backend servers to sync your frontend forms with your sales database. Running `list_forms` allows your application to match user inputs with your active CRM fields on the fly.

Direct conversational triggers and messaging

The `send_message` tool lets your Vercel AI SDK agent dispatch SMS or email responses directly from your customer-facing chat interface. You hook this up to your streaming text generation to trigger immediate follow-ups based on live conversations. Monitoring these interactions is straightforward with `list_conversations`. Your agent scans previous chats to ground its responses, ensuring your users never receive repetitive messages.

Setup guide

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

Install `@ai-sdk/mcp` and initialize the client using the Vinkius URL. This connects your application to the MCP Server instantly. Pass the tools from `mcpClient.tools()` directly into `generateText` or `streamText`, and remember to call `mcpClient.close()` when you are done so you don't leak memory.

Yes, the server runs on Vinkius and connects over lightweight HTTP, making it fully compatible with Vercel Edge runtime constraints. Your agent can run `list_campaigns` and `list_calendars` without hitting cold starts or execution limits.

Vinkius manages the connection pooling and handles the base API authentication. If your agent calls `list_contacts` repeatedly, the SDK handles the stream, but you should implement local caching for heavy operations like `list_opportunities`.

Yes. The agent uses `list_calendars` to fetch available booking slots from your CRM. It can then present these slots to the user in the chat UI and trigger a contact update to book the slot.

Your CRM contacts and message history are never stored on Vinkius. The MCP Server acts as an ephemeral proxy inside a zero-trust V8 sandbox, routing requests to GoHighLevel and passing the raw data directly to your local runtime.

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