How to Use the Checkly MCP in Vercel AI SDK

Q: How do I trigger a Checkly test run inside a Vercel AI SDK stream?

Use triggercheckrun inside your tool definitions. You initialize the connection using createMCPClient and pass the tools directly to streamText to push test results to your frontend.

Q: How do I manage connection lifecycles when calling Checkly with Vercel AI SDK?

Always call mcpClient.close() once your streaming session finishes. This prevents lingering HTTP connections in your serverless or edge environments.

Q: What package do I need to connect my AI client to this endpoint?

Install ai and @ai-sdk/mcp via npm. Pass the hosted Vinkius URL to the client configuration to expose the monitoring tools to your model.

Get real-time Checkly monitoring data and run instant checks directly inside your Vercel AI SDK streaming UI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Checkly MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live Checkly runs using this MCP Server.

`trigger_check_run` executes a specific Checkly test immediately so your users don't wait on background queues. The Vercel AI SDK streams these live execution states directly to your React or Next.js components. You see the test run, pull `get_check_performance_metrics` to grab raw latency numbers, and watch the UI update in real time. Your edge functions stay fast because this setup avoids heavy client-side polling. We grab the live performance data, pipe it to your agent, and close the connection using `mcpClient.close()` when the stream ends.

Fast incident diagnosis in your UI

`get_check_details` pulls the exact failure state and configuration of any failing monitor in your account. Your agent uses this tool alongside `list_checkly_checks` to map out which endpoints are down. It displays the broken assertions right inside your chat interface before the user even asks. Instead of jumping back and forth between browser tabs, your frontend displays the failure details immediately. You write the streaming code using the MCP client creator and feed the tools array to `streamText` for a low-latency debugging experience.

Real-time alert channel audits

`list_checkly_alert_channels` reads your active notification destinations like Slack, Email, or PagerDuty to verify where alerts go. Your streaming UI displays these routes alongside `list_check_groups` so you can verify if a failing API group has the right team on call. You build this interface using the standard `@ai-sdk/mcp` package. This allows your user-facing tools to inspect alerting structures without exposing raw API keys to the browser client.

Setup guide

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

Use `trigger_check_run` inside your tool definitions. You initialize the connection using `createMCPClient` and pass the tools directly to `streamText` to push test results to your frontend.

Yes, this setup is fully compatible with Edge Functions. The `get_check_performance_metrics` tool returns raw JSON data that streams to your UI without blocking the main thread.

Always call `mcpClient.close()` once your streaming session finishes. This prevents lingering HTTP connections in your serverless or edge environments.

Install `ai` and `@ai-sdk/mcp` via npm. Pass the hosted Vinkius URL to the client configuration to expose the monitoring tools to your model.

We run every MCP Server in an isolated V8 sandbox that destroys itself after execution. Your API keys, alert configurations, and raw test payloads never persist on our servers.

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