How to Use the Better Stack MCP in Mastra AI

Q: How do I require human approval for Better Stack actions in Mastra AI?

Flag specific tools like resolveincident with the approval requirement in your configuration. The agent will halt execution and wait for a developer to sign off before changing the alert state.

Build resilient incident response workflows. Mastra AI and this MCP Server handle the conditional logic when your infrastructure breaks.

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 Mastra AI

Create your Vinkius account to connect Better Stack to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Smart Escalation with Mastra AI

Running `list_incidents` every minute inside a workflow lets you catch new fires instantly. Things break at the worst possible times. If a critical system goes down, the agent automatically evaluates the severity before deciding what to do next. Mastra handles the conditional branching natively. When the payload indicates a tier-one outage, the workflow immediately triggers `list_on_call` to find the primary engineer. The system pages them, waits for a response, and retries with an escalation path if they ignore it.

Safe Incident Resolution via MCP Server

Setting `requireToolApproval` on the `resolve_incident` tool forces the agent to pause and ask for human confirmation. You probably don't want an autonomous script closing active alerts blindly. An engineer reviews the proposed fix before anything actually changes in production. This prevents premature closures of ongoing outages. Once the human clicks approve, the tool executes and clears the alert. Your team stays in control while the workflow engine does the heavy lifting of gathering context.

Track Heartbeats with Exponential Backoff

Fetching node details with `get_heartbeat` might fail if the API drops a connection, but Mastra handles it. Network blips cause false positives all the time. The framework automatically catches that failure and retries the request using exponential backoff. You never have to write custom retry logic again. The agent grabs the full monitor list via `list_monitors` and maps out the current state of your infrastructure. If a transient error occurs, the workflow just waits a few seconds and tries the endpoint one more time.

Setup guide

Set up Better Stack MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Better Stack tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "better-stack-1-mcp-client",
  servers: {
    "better-stack-1-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Better Stack Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Better Stack tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Better Stack transactions"
);
console.log(result.text);

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 Mastra AI

Install the integration package and instantiate a new client with your Vinkius URL. Call the tool listing method and spread the result directly into your agent's tool array. The framework automatically detects whether to use SSE or HTTP transport.

Yes, as long as you configure the workflow to do so. Your agent can read the alert and immediately fire `acknowledge_incident` to stop the paging noise.

The workflow engine catches the rejection and applies an automatic retry with exponential backoff. Your incident fetching job will pause briefly before attempting to read the data again.

Flag specific tools like `resolve_incident` with the approval requirement in your configuration. The agent will halt execution and wait for a developer to sign off before changing the alert state.

Vinkius manages your connection through a secure, ephemeral proxy. Your specific on-call routing calendars and engineer contact details remain strictly isolated. The authentication token handles the request, and the sandbox vanishes the moment the workflow completes.

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