How to Use the Better Stack MCP in OpenAI Agents SDK

Let your OpenAI Agents SDK monitor production and manage Better Stack incidents with built-in safety guardrails.

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 OpenAI Agents SDK

Create your Vinkius account to connect Better Stack to OpenAI Agents 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe incident triage with OpenAI Agents SDK

When an alert fires, your Python agent grabs details using `get_incident` to diagnose the issue. The SDK's guardrails prevent the agent from making rogue modifications while it scans recent problems with `list_incidents`. Your agent can hand off the task to a specialized on-call agent. That agent checks who is active using `list_on_calls` and updates the team, keeping the entire triage loop safe and fully logged in your OpenAI dashboard.

Automated monitor management via MCP Server

Stop writing custom scripts to provision uptime checks. This MCP Server lets your agent run `create_monitor` and `update_monitor` based on your live deployment configurations. OpenAI's framework ensures these tool calls pass through your validation layers before hitting Better Stack. If a check fails, the agent can clean up by calling `delete_monitor` without human intervention.

Real-time status and heartbeat tracking

Your agent keeps track of background jobs by calling `list_heartbeats` to find silent failures. It cross-references these with public-facing status pages using `list_status_pages`. Because the OpenAI Agents SDK handles complex multi-agent flows, one agent can monitor the heartbeats while another pulls specific monitor configs via `get_monitor`. You get a clear trace of every tool call in your dashboard.

Setup guide

Set up Better Stack MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Better Stack tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Better Stack tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Better Stack tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Better Stack Agent",
            instructions="You have access to Better Stack tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the SDK and pass the Vinkius HTTP endpoint to your agent constructor using `MCPServerStreamableHttp`. The SDK auto-discovers all ten Better Stack tools instantly. You just need to set `cacheToolsList=True` to keep execution fast.

Yes, if you configure your agent to do so. The agent can fetch the issue using `get_incident`, find the on-call engineer with `list_on_calls`, and update the monitor via `update_monitor`. The SDK's built-in guardrails ensure the agent doesn't execute unauthorized API calls.

The SDK manages tool execution flow, but the underlying Vinkius platform handles connection stability. If your agent spams `list_monitors` or `list_heartbeats`, the platform manages the HTTP transport to keep your production runs clean.

No. The OpenAI Agents SDK automatically reads the schema from the MCP Server endpoint. Your agent immediately understands how to format arguments for `create_monitor` or `get_monitor` without manual JSON mapping.

Vinkius runs this MCP server in an isolated V8 sandbox, meaning your API tokens never leak to the LLM. The agent only receives the raw text output from tools like `list_incidents` or `get_monitor`. No raw credentials ever enter the OpenAI prompt context.

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