How to Use the Kolide MCP in OpenAI Agents SDK

Q: How do I connect Kolide to my OpenAI Agents SDK project?

Use the MCPServerStreamableHttp class to point your agent at the server URL. Once you pass it into the constructor, the SDK automatically maps the tools for you.

Q: Can OpenAI Agents SDK run security checks automatically?

Yes, you can script your agent to call listkolidechecks on a schedule. It will then compare your fleet status against those requirements.

Audit your fleet directly within OpenAI Agents SDK. Stop guessing about device security and start acting on real-time Kolide data.

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 OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time fleet security visibility

Stop jumping between dashboards to check if your endpoints are secure. This MCP Server lets your agent pull live data using `list_kolide_devices` and `get_device_details` to verify compliance on the fly. Your agent automatically processes these inputs, ensuring every device in your inventory meets your security baseline without manual oversight.

Automated security issue tracking

Identify vulnerabilities before they become incidents by querying `list_kolide_issues` and `get_issue_details`. Your agent gains immediate context on what's failing across the fleet. Once an issue is identified, the agent can cross-reference it with `get_person_details` to see exactly who needs to remediate their workstation.

High-level fleet health monitoring

Keep a pulse on your organization with `get_kolide_fleet_stats`. Instead of parsing raw logs, your agent summarizes total device counts and online status into clear, actionable reports. This keeps your team focused on the metrics that matter, allowing the agent to flag anomalies in the audit trail generated by `list_kolide_audit_logs`.

Setup guide

Set up Kolide 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 Kolide tools at runtime.
3

Create your Agent

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

Run the agent

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

Use the `MCPServerStreamableHttp` class to point your agent at the server URL. Once you pass it into the constructor, the SDK automatically maps the tools for you.

Yes, you can script your agent to call `list_kolide_checks` on a schedule. It will then compare your fleet status against those requirements.

Yes, the agent validates all tool outputs against its internal logic. If the data from `get_device_details` looks malformed, the guardrails catch it before it reaches your workflow.

Your device and user data stays local to the agent's context. We don't store your logs; the server only facilitates the connection between your endpoint and the API.

The agent will receive an error response from the tool. You should handle this in your code to retry the request or alert your admin team.

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