How to Use the Checkmk MCP in AutoGen

Q: How do I load Checkmk tools into an AutoGen agent?

Install the autogen-extmcp package. Pass your Vinkius URL to mcpservertools using StreamableHttpServerParams, and hand the resulting list to your AssistantAgent constructor.

Q: What happens if an agent tries to query a non-existent host?

The gethostdetails tool returns an error string. The agent reads this failure, discusses the typo with its peers, and retries the request with the corrected hostname.

Give your AutoGen agents the ability to debate infrastructure changes and interact with Checkmk before committing updates.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Checkmk MCP to AutoGen

Create your Vinkius account to connect Checkmk 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 Checkmk with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map topology with AutoGen

Complex network issues rarely have one obvious cause. Your multi-agent setups can pull apart monitoring data, argue over the root cause, and agree on a fix. An investigator agent runs `list_checkmk_hosts` and `list_host_services` to gather the raw facts. It passes this payload to a specialized database agent, which cross-references the alerts before deciding if the server actually needs attention.

Negotiate configuration changes

You never want an LLM blindly pushing updates to your monitoring core. By splitting responsibilities across different roles, you create a built-in review process. One agent proposes a new folder structure using `list_checkmk_folders`. A security-focused agent reviews the plan, suggests modifications, and only allows the `activate_checkmk_changes` call once both sides reach consensus.

Audit group alignments via this MCP Server

Misconfigured service clusters create massive blind spots in your alerting logic. Autonomous workers can continuously audit these groupings in the background. The system pulls current definitions via `list_host_groups` and `list_service_groups`. The agents debate whether the current layout matches your operational guidelines, flagging any rogue machines that slipped outside the standard policies.

Setup guide

Set up Checkmk 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 Checkmk 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="Checkmk_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Checkmk 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="Checkmk_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Checkmk 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 Checkmk. 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 Checkmk 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 Checkmk MCP in AutoGen

Install the autogen-ext[mcp] package. Pass your Vinkius URL to mcp_server_tools using StreamableHttpServerParams, and hand the resulting list to your AssistantAgent constructor.

Yes. You load the toolset once and distribute specific capabilities to different agents. The McpToolAdapter handles all the schema conversions automatically.

The `get_host_details` tool returns an error string. The agent reads this failure, discusses the typo with its peers, and retries the request with the corrected hostname.

Definitely. You can configure your conversation flow so the agents deliberate, draft the fix, and pause. They wait for your terminal input before executing the final commit command.

Only to your own environment. The zero-trust Vinkius isolate processes the API requests for your hostnames and folder paths, then immediately wipes its memory. No persistent storage means zero risk of data leakage.

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