How to Use the PushEngage MCP in Vercel AI SDK

Q: How do I stream PushEngage notification metrics with Vercel AI SDK?

Use listpushengagenotifications inside your tool definition block. The Vercel AI SDK streams the resulting list of sent alerts directly into your React component as the LLM processes the payload.

Q: Can Vercel AI SDK trigger a PushEngage broadcast dynamically?

Yes. Your agent can call sendpushengagebroadcast based on user prompts. The Vercel AI SDK then handles the tool execution, letting you watch the confirmation stream into your chat window in real-time.

Q: How does Vercel AI SDK fetch subscriber counts from PushEngage?

The SDK calls listpushengagesubscribers through the MCP Server. It reads the subscriber list and feeds the raw numbers directly to your UI components without requiring custom backend endpoints.

Q: How do I close the connection after listing PushEngage sites?

Always call mcpClient.close() once you finish running listpushengagesites. This cleans up active transport channels in your Edge Functions and prevents memory leaks.

Broadcast browser notifications and analyze subscriber segments directly within your Vercel AI SDK streaming interface.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect PushEngage MCP to Vercel AI SDK

Create your Vinkius account to connect PushEngage to Vercel AI SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup PushEngage with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Real-time PushEngage broadcast status in Vercel AI SDK

Connect your Vercel AI SDK streaming interface to PushEngage browser alerts without waiting for slow API responses. When your agent calls `send_pushengage_broadcast`, the Vercel AI SDK pushes the dispatch status straight to the user's viewport. No annoying loading spinners or frozen UI elements while the server processes the PushEngage request. Your Next.js app displays the progress of the notification run step-by-step. By rendering the tool output as it arrives, Vercel AI SDK keeps users informed while the MCP Server handles the actual handshake with the PushEngage browser push network.

Interactive segment analysis

Let users filter PushEngage subscriber lists using natural language inside your Vercel AI SDK chat UI. The agent calls `list_pushengage_segments` to pull current groups, then maps them to the active Vercel AI SDK UI state. Because Vercel AI SDK handles PushEngage tool outputs natively, these segments render as interactive UI components. You can immediately pass these filtered PushEngage lists to other operations, making database querying feel like a conversation.

Live status and trigger monitoring

Keep tabs on active automated PushEngage campaigns without refreshing a single Vercel AI SDK interface. The agent checks system health via `check_pushengage_status` and pulls automated workflows using the MCP Server in the background. This setup lets you build a live monitoring dashboard where the Vercel AI SDK streams PushEngage updates directly to your screen. You see exactly when a PushEngage trigger goes offline or when subscriber activity spikes, keeping your marketing stack online.

Setup guide

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

Use `list_pushengage_notifications` inside your tool definition block. The Vercel AI SDK streams the resulting list of sent alerts directly into your React component as the LLM processes the payload.

Yes. Your agent can call `send_pushengage_broadcast` based on user prompts. The Vercel AI SDK then handles the tool execution, letting you watch the confirmation stream into your chat window in real-time.

The SDK calls `list_pushengage_subscribers` through the MCP Server. It reads the subscriber list and feeds the raw numbers directly to your UI components without requiring custom backend endpoints.

Always call `mcpClient.close()` once you finish running `list_pushengage_sites`. This cleans up active transport channels in your Edge Functions and prevents memory leaks.

Yes. The server handles subscriber IDs and segment details inside an isolated V8 sandbox. Your API keys never touch the client browser, keeping your PushEngage subscriber records secure.

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