How to Use the Dripcel MCP in Vercel AI SDK

Q: Can I stream Dripcel template lists directly to a React component using Vercel AI SDK?

Yes, you can. By calling listwhatsapptemplates within the SDK's streaming text generation, the agent outputs the available templates directly to the UI as they are returned from the server.

Q: What happens if a Dripcel instance disconnects while a Vercel AI SDK session is active?

The SDK catches the connection error from getwhatsappconnectionstatus and streams a fallback message to the user. You can handle this gracefully in your UI without crashing the Node or Edge process.

Q: How do I clean up the connection after sending a message?

Always call mcpClient.close() when your execution block finishes. This prevents open HTTP or SSE connections from lingering in your MCP environment and racking up execution costs.

Feed live WhatsApp delivery updates and instance metrics directly to your Next.js UI using 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 Dripcel MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live UI updates with Vercel AI SDK

When you trigger a WhatsApp message, waiting for a spinner sucks. This setup lets your Vercel AI SDK application stream the action live as it happens. Your users watch the agent invoke `send_whatsapp_message` and instantly see the outcome in their browser window. You don't have to write custom polling logic or handle complex websockets on your own. The connection uses this MCP Server to pipe raw status updates straight from the Dripcel API into your component state.

Instant contact lookups at the edge

Edge functions need to run fast, and this setup fits right in. Your agent can run `search_instance_contacts` inside a lightweight Vercel routing path without pulling in heavy database dependencies. It keeps your bundle size small and your response times under a hundred milliseconds. The agent checks the Dripcel directory on the fly to match incoming phone numbers with existing customer records.

Real-time instance monitoring

Keep tabs on your messaging pipelines without reloading your dashboard. The SDK hooks directly into `quick_instance_health_audit` to render active connection states as they change. If a connection drops, your UI updates the status badge immediately. This MCP setup keeps your support team informed without requiring manual page refreshes or API polling.

Setup guide

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

You pass your Dripcel API key as an environment variable to your edge runtime. When you initialize the MCP client with `createMCPClient`, it securely forwards the token to authorize your requests.

Yes, you can. By calling `list_whatsapp_templates` within the SDK's streaming text generation, the agent outputs the available templates directly to the UI as they are returned from the server.

The SDK catches the connection error from `get_whatsapp_connection_status` and streams a fallback message to the user. You can handle this gracefully in your UI without crashing the Node or Edge process.

Always call `mcpClient.close()` when your execution block finishes. This prevents open HTTP or SSE connections from lingering in your MCP environment and racking up execution costs.

All raw text payloads and recipient phone numbers pass through an ephemeral, zero-trust V8 sandbox. No message content is cached or stored on the proxy server; it goes straight to the API and vanishes.

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