How to Use the Keap MCP in Vercel AI SDK

Q: How do I connect Keap to the Vercel AI SDK?

Use createMCPClient with an HTTP transport pointing to your Vinkius endpoint. Then call mcpClient.tools() and pass the array into your generateText or streamText function.

Q: How do I close the connection after updating a contact?

Always call mcpClient.close() once your stream finishes. Leaving it open wastes resources on your server.

Build real-time sales dashboards in React by connecting Keap to 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 Keap MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Keap data into your Vercel AI SDK UI

`list_contacts` and `get_contact` fetch CRM records straight from the source. Your user types a name, and the agent pulls the exact profile details without making them wait for a full page reload. This MCP Server handles the backend communication while you focus on the interface. Because Vercel handles the streaming, the front end renders the contact's phone number and email instantly. You don't build custom loading states; you just pass the tool results straight into `streamText`.

Render live ecommerce and invoice history

`list_orders` pulls the complete transaction history for any customer in your database. The agent checks what they bought last week and formats the response as a live React component. If a customer asks about a missing receipt, the agent hits `list_invoices` to find the exact billing record. The Vercel edge function processes the tool call and streams the invoice amount directly back to the chat window.

Update CRM records from user chat

`create_contact` takes a first name or email from the chat prompt and writes a new lead into your database. The user never leaves the conversation to fill out a web form. After creating the lead, the agent runs `apply_tag_to_contact` to categorize them based on what they just discussed. The MCP Server handles the API transaction while your UI updates to show the successful registration.

Setup guide

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

Use `createMCPClient` with an HTTP transport pointing to your Vinkius endpoint. Then call `mcpClient.tools()` and pass the array into your `generateText` or `streamText` function.

Yes. The MCP protocol communicates over standard HTTP, so your edge-deployed Next.js route handlers can talk to the server without cold start delays.

No. Vinkius manages the OAuth handshake for you. You just pass your endpoint token into the `authProvider` configuration.

Always call `mcpClient.close()` once your stream finishes. Leaving it open wastes resources on your server.

The server processes raw ecommerce orders and contact emails. Vinkius runs the integration inside an ephemeral V8 Isolate Sandbox, meaning your transaction data exists only during the tool call and is destroyed immediately after.

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