How to Use the Kolide MCP in LangChain

Q: What's the best way to monitor fleet health with Kolide in LangChain?

Build a simple chain that calls getkolidefleetstats on a timer. You can have your agent check the totalissuescount and alert you only when it crosses a certain threshold. It's a simple, effective way to keep an eye on things without constant dashboard checks.

Chain Kolide tool calls in LangChain to build automated device security and compliance workflows.

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 LangChain

Create your Vinkius account to connect Kolide to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Fleet Auditing

Stop pulling device lists by hand. Build a chain that calls `list_kolide_devices` to get all your endpoints, then loops through the results, passing each ID to `get_device_details` for a full hardware and software inventory. Your agent can then cross-reference that data against your own asset management database. This isn't just a one-off report; it's a repeatable process you can run on a schedule to catch configuration drift before it becomes a problem.

Build a Security Triage Agent

Give your LangChain agent the tools to act like a security analyst. It can start by calling `list_kolide_issues` to find open, high-priority problems across your fleet. From there, it uses the issue ID to run `get_issue_details` to find out which device and person are involved. Finally, the agent can use `get_person_details` to find the user's manager for escalation. You just built a Level 1 triage bot that handles the repetitive part of incident response, freeing up your team for actual analysis.

Connect this MCP Server to Other Tools

Kolide data is good. Kolide data connected to your other systems is better. Use this MCP server to pull fleet stats and then pass them to another tool in your chain—like a database loader or a metrics dashboard. For example, create a daily digest chain. It starts with `get_kolide_fleet_stats` for a high-level summary and `list_kolide_audit_logs` for key events. Then it formats the output and sends it to a messaging tool. All in one automated sequence.

Setup guide

Set up Kolide MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Kolide tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "kolide-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Kolide transactions"
    })
    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 LangChain

First, install the Vinkius adapter for LangChain. Then, point it to your Kolide MCP Server endpoint URL. The adapter's `get_tools()` method will give you a list of functions to pass directly into your agent executor.

This tool set is read-only for safety. Your agent can identify issues, find owners with `get_person_details`, and gather all context using tools like `get_issue_details`, but it can't change device state. You'd use that output to trigger a separate remediation workflow.

Build a simple chain that calls `get_kolide_fleet_stats` on a timer. You can have your agent check the `total_issues_count` and alert you only when it crosses a certain threshold. It's a simple, effective way to keep an eye on things without constant dashboard checks.

Yes, it works perfectly. You can define nodes in your graph where each node's job is to call a specific Kolide tool, like `list_kolide_devices`. This lets you build complex, stateful security workflows that can loop, branch, and retry based on the data returned.

Your Kolide fleet data, like device serial numbers or user names, only exists in the memory of your LangChain agent during a single run. The MCP Server itself is ephemeral and doesn't store anything. Unless you explicitly code your agent to save the data, it's gone once the chain finishes.

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