How to Use the Netdata MCP in AutoGen

Q: How do I load Netdata MCP tools into an AutoGen assistant?

Install autogen-extmcp. Initialize mcpservertools with your endpoint URL, and pass the resulting list directly into your AssistantAgent constructor.

Q: Can multiple AutoGen agents share the Netdata connection?

Yes. The McpToolAdapter handles the schema conversion for all agents in the conversation. They all query the same server endpoint without conflicting.

Build multi-agent SRE teams. AutoGen agents debate Netdata metrics via this MCP Server, analyze alerts, and negotiate scaling decisions.

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 AutoGen

Create your Vinkius account to connect Netdata to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Netdata Alarm Triage

One agent rarely catches every edge case during an outage. You spin up a performance agent and a stability agent. They use `get_alarms` to pull the active incident list and start deliberating. The performance agent checks `get_chart_data` to argue that CPU load is acceptable. The stability agent counters by pulling `get_all_metrics` to show memory swapping. They negotiate a consensus before notifying the on-call engineer.

Autonomous Node Discovery and Mapping

Hardcoded dashboards rot. Your AutoGen setup uses an explorer agent that constantly maps your environment. It runs `list_spaces` and `list_rooms` to find new infrastructure as it spins up. When it finds an unmapped cluster, it triggers `list_room_nodes`. It then hands that list to a configuration agent, which uses `get_agent_info` to verify the Netdata daemon version on each new machine.

Debate-Driven Netdata MCP Server Analysis

Complex performance issues require competing perspectives. You assign the `list_charts` tool to a specialized diagnostic agent. It identifies the most relevant disk I/O charts for a failing node. A separate root-cause agent queries `list_space_alerts`. The two agents cross-examine the data. They do not stop interacting until their analysis of the active alarms matches the historical chart telemetry.

Setup guide

Set up Netdata MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Netdata tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Netdata_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Netdata data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Netdata_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Netdata data")
    print(result.messages[-1].content)

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 AutoGen

Install `autogen-ext[mcp]`. Initialize `mcp_server_tools` with your endpoint URL, and pass the resulting list directly into your `AssistantAgent` constructor.

Yes. The `McpToolAdapter` handles the schema conversion for all agents in the conversation. They all query the same server endpoint without conflicting.

You provide system prompts defining their roles. A networking agent naturally gravitates toward `get_chart_data` for bandwidth metrics, while an SRE agent prioritizes `get_alarms`.

You configure max conversational turns in the framework. This stops the agents from infinitely looping `get_all_metrics` if they cannot agree on the root cause.

Vinkius isolates the execution completely. The agents fetch system metrics and node IDs through a secure, ephemeral sandbox. No telemetry persists on our infrastructure once the multi-agent 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