How to Use the Kolide MCP in AutoGen

Q: What's a good starting agent setup for Kolide and AutoGen?

Start with two: a UserProxyAgent that you can talk to, and an AssistantAgent that has the Kolide tools. Ask it, "Check our fleet status." The assistant will likely decide to run getkolidefleetstats and show you the results. From there, you can build out more specialized agents.

Have AutoGen agents debate and collaborate to investigate and report on Kolide security issues.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kolide MCP to AutoGen

Create your Vinkius account to connect Kolide 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 Kolide with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Set Up an Agent Security Team

Go beyond single-agent execution. Create a team of specialized AutoGen agents that talk to each other to solve problems. One agent, the 'Auditor', is responsible for running `list_kolide_issues` to find new problems. When the Auditor finds something, it passes the details to the 'Investigator' agent. The Investigator's job is to use `get_issue_details` and `get_device_details` to gather all the context. They work together, just like a real SOC team.

Debate Issue Severity and Priority

Some issues aren't clear-cut. Set up two agents with competing goals to debate the right course of action. An 'IT Ops' agent might use `get_person_details` to argue an issue affects a key executive and needs immediate attention. A 'Compliance' agent could counter by using `list_kolide_checks` to show that while the issue is visible, it doesn't violate any critical controls. Through conversation, they arrive at a more nuanced conclusion than a single agent could, and present the final recommendation to you.

Automate Incident Post-Mortems

Use a multi-agent conversation to document an incident. After an issue is resolved, trigger a workflow. One agent's job is to pull the full history from `list_kolide_audit_logs`. Another agent interviews the first, asking clarifying questions about the timeline. A third 'Writer' agent observes the conversation and drafts a summary report. This MCP Server gives your agents the raw data they need to build a factual, detailed report of what happened and why.

Setup guide

Set up Kolide 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 Kolide 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="Kolide_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You provide the list of Kolide tools from this MCP Server to your `AssistantAgent`. The agent can then decide which tool to call based on the ongoing conversation with other agents or the user. AutoGen handles the function calling automatically.

Start with two: a `UserProxyAgent` that you can talk to, and an `AssistantAgent` that has the Kolide tools. Ask it, "Check our fleet status." The assistant will likely decide to run `get_kolide_fleet_stats` and show you the results. From there, you can build out more specialized agents.

Yes, that's the point of AutoGen. You can have one agent looking up device details with `get_device_details` while another agent looks up the owner's info with `get_person_details`. They share their findings in the group chat to solve the problem faster.

Absolutely. The entire conversation between agents is logged. You can see why the 'Auditor' agent chose to flag an issue from `list_kolide_issues` and review the 'Investigator' agent's logic for escalating it. This transparency is key for trusting the system.

Your Kolide fleet data, including device details and user lists, exists within the conversation history of your agent group chat. The security of this data depends on how you manage those logs. The MCP Server doesn't retain any of it; it just answers the API calls from your agents.

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