How to Use the Better Stack MCP in Vercel AI SDK

Q: What happens if a heartbeat check fails during a streaming session?

Your agent will detect the failure when it calls listheartbeats. The Vercel AI SDK immediately streams the down status to your UI components. Your users see the offline alert instantly, allowing them to react before standard email notifications arrive.

Pipe live Better Stack uptime metrics and incident updates directly into your React frontend 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 Better Stack MCP to Vercel AI SDK

Create your Vinkius account to connect Better Stack 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 Better Stack with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live React Uptime Feeds via Vercel AI SDK

This Vercel AI SDK configuration connects your frontend to the Better Stack MCP Server. Instead of waiting for a slow backend fetch, your streaming UI shows users exactly when a ping fails. Your app calls `list_monitors` and feeds the raw status directly into a React component as the LLM processes the data. You write standard Next.js code, and the SDK handles the heavy lifting. The server processes `get_monitor` requests on Vercel Edge Functions without slowing down your user interface. When an API goes dark, your users see the incident timeline build letter by letter.

Instant Incident Escalation

The `list_incidents` tool lets your streaming agent pull down active outages and present them to your operations team. When an engineer clicks resolve, the SDK triggers `get_incident` to verify the status. You don't have to build custom API polling or state sync logic. Your agent can draft post-mortems using the fetched data. It runs `list_on_calls` to find who's awake, then displays the active rotation schedule right inside the chat window. This cuts down the time between a server crash and getting the right engineer on a call.

Interactive Monitor Editing

Let your users modify their check intervals by chatting with your UI. The agent calls `update_monitor` to adjust timeout thresholds on the fly. You feed these MCP tool definitions directly into `streamText` to keep the user interface in sync. If a user wants to tear down a legacy test, the agent runs `delete_monitor` after a quick confirmation. Every change reflects instantly in your custom dashboard without requiring a manual browser refresh.

Setup guide

Set up Better Stack 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 Better Stack 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 Better Stack 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 Better Stack. 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 Better Stack 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 Better Stack MCP in Vercel AI SDK

You configure authentication by passing your token to the Vercel AI SDK client setup. Use the `authProvider` option inside `createMCPClient` to securely forward your Better Stack credentials. This ensures your edge functions can safely call `list_monitors` without leaking API keys to the frontend.

Yes, this setup is fully compatible with Edge runtimes. The Vercel AI SDK connects to the hosted Better Stack endpoint using lightweight HTTP transport, avoiding heavy Node.js dependencies. You can fetch `list_heartbeats` or monitor updates within global edge locations under 50ms.

The SDK relies on the underlying MCP client to handle network throttling. If you run multiple instances of `list_incidents`, the client manages the queue to avoid hitting Better Stack API ceilings. You can also implement custom middleware to debounce rapid agent requests.

Your agent will detect the failure when it calls `list_heartbeats`. The Vercel AI SDK immediately streams the down status to your UI components. Your users see the offline alert instantly, allowing them to react before standard email notifications arrive.

Yes, it is fully protected. All communication between your AI agent and the Better Stack endpoint is encrypted via HTTPS within a zero-trust sandbox. The server only reads your uptime monitors, heartbeats, and on-call schedules when your agent explicitly invokes a tool like `list_on_calls`. No credentials or server logs are ever stored on Vinkius.

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