How to Use the Kolide MCP in LlamaIndex

Q: How do I connect the Kolide MCP Server to LlamaIndex?

Use the McpToolSpec from the LlamaIndex tools library. You just give it your server endpoint URL. It handles fetching the tools and converting them into a format that a LlamaIndex agent can use directly.

Q: Can I search across different types of Kolide data with LlamaIndex?

Yes. You can create a single index containing data from listkolidedevices, listkolideissues, and listkolidepeople. LlamaIndex can then perform complex queries across all that data to answer questions that require joining information, like "Which users have the most open issues?"

Q: Can I filter which Kolide tools my LlamaIndex agent can use?

Yes, the McpToolSpec allows you to specify exactly which tools the agent should have access to. If you only want an agent to be able to list issues and devices, you can restrict it to just listkolideissues and listkolidedevices.

Index your Kolide fleet data with LlamaIndex to create a searchable knowledge base of your security posture.

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 LlamaIndex

Create your Vinkius account to connect Kolide to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Your Device Inventory

Turn your entire device list into a queryable object. Use the MCP tool spec to load all devices from `list_kolide_devices` and index them. Once indexed, you can ask natural language questions about your fleet. Instead of scripting, just ask: "How many MacBooks have FileVault disabled?" or "List all Windows devices that haven't checked in for 30 days." LlamaIndex will translate your question into the right queries against the indexed data.

Analyze Security Issue Trends

Don't just list current issues; understand their history. Periodically run `list_kolide_issues` and ingest the results into a LlamaIndex vector store. This builds a historical record of your security posture over time. Now your RAG application can answer questions like, "What were the most common security issues in Q2?" or "Show me the timeline for issue #512." Your agent finds answers grounded in your actual Kolide data, not guesswork.

Build a Compliance RAG Agent

Combine Kolide's live data with your own internal compliance documents. First, index your security policies. Then, give your LlamaIndex agent access to this MCP Server to pull live device status with tools like `get_device_details`. When you ask, "Is device ID 123 compliant with our data encryption policy?", the agent checks your policy documents and then uses the tools to get the device's real-time encryption status from Kolide. You get a complete, evidence-based answer.

Setup guide

Set up Kolide MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Kolide MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Kolide tools.",
)
response = await agent.run("List recent Kolide data")

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 LlamaIndex

Use the `McpToolSpec` from the LlamaIndex tools library. You just give it your server endpoint URL. It handles fetching the tools and converting them into a format that a LlamaIndex agent can use directly.

Yes. You can create a single index containing data from `list_kolide_devices`, `list_kolide_issues`, and `list_kolide_people`. LlamaIndex can then perform complex queries across all that data to answer questions that require joining information, like "Which users have the most open issues?"

Build a security help desk bot. Index your Kolide fleet data and your internal IT wiki. When a user asks a question, the bot can check both sources to see if it's a known device issue or something that needs a wiki article, providing a much more useful answer.

Yes, the `McpToolSpec` allows you to specify exactly which tools the agent should have access to. If you only want an agent to be able to list issues and devices, you can restrict it to just `list_kolide_issues` and `list_kolide_devices`.

The MCP Server itself is stateless. When you use LlamaIndex, you are explicitly pulling Kolide fleet data—like device names and issue logs—and storing it in your own vector database. The security of that data is your responsibility; you control the database, its access policies, and its encryption.

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