How to Use the Netdata MCP in OpenAI Agents SDK

Give your OpenAI Agents SDK production guardrails for real-time Netdata infrastructure telemetry.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Netdata MCP to OpenAI Agents SDK

Create your Vinkius account to connect Netdata 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 Netdata with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Netdata MCP Server Telemetry

The Netdata MCP server connects your OpenAI Agents SDK deployment directly to live infrastructure metrics. You pass the server instance to your Agent constructor, and it auto-discovers tools like `get_all_metrics` and `get_chart_data` without manual schema mapping. Production safety relies on accurate data. Setting `cacheToolsList=True` keeps your agent's context window light while it actively polls `list_charts` to track CPU spikes or memory leaks across your cluster.

Automated Incident Handoffs

Complex outages require specialized MCP tools to parse different telemetry streams. One agent can watch `list_space_alerts` for high-level cloud warnings, then hand off execution to a diagnostic agent. That secondary agent immediately pulls `get_alarms` for specific nodes. OpenAI's built-in tracing records exactly which charts the agent queried, giving your team a complete audit trail of the automated response.

Multi-Node Cloud Discovery

Hardcoding IP addresses breaks when infrastructure scales. Your MCP agent maps your entire Netdata Cloud topology dynamically by chaining `list_spaces`, `list_rooms`, and `list_room_nodes`. Guardrails prevent the agent from executing destructive actions, keeping it focused on read-only discovery. It uses `get_agent_info` to verify node health before logging the current state to your OpenAI dashboard.

Setup guide

Set up Netdata 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 Netdata tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Netdata 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="Netdata Agent",
            instructions="You have access to Netdata 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 Netdata. 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 Netdata 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 Netdata MCP in OpenAI Agents SDK

Use the MCPServerStreamableHttp class with your endpoint URL. Pass it into the mcp_servers list when initializing your agent. The SDK auto-discovers all ten tools immediately.

Yes, the dashboard logs every tool invocation. When your agent calls `list_space_alerts`, you see the exact payload and latency in your trace history.

Set cacheToolsList=True to reduce overhead on the initialization phase. You should also instruct your agent to query `get_chart_data` only after an alarm triggers, rather than polling constantly.

Handoffs work natively with these tools. A triage agent can fetch `list_space_nodes` and route the specific node ID to a debugging agent for deeper analysis.

The server only reads system metrics, active alarms, and node topology data like CPU usage or memory limits. Vinkius runs this connection inside an ephemeral V8 Isolate Sandbox, meaning your raw telemetry passes through memory and disappears the moment the session ends.

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