How to Use the Kolide MCP in Vercel AI SDK

Q: How can I use the Vercel AI SDK to list all Kolide devices with open issues?

Your agent can call listkolideissues to get all current problems, then use getdevicedetails for each affected device. The AI SDK streams this combined data right into your UI components, so you can build a live list of at-risk devices and their owners.

Q: What's the best way to get started?

Install the @ai-sdk/mcp package and point your createMCPClient to the Vinkius endpoint token you were given. The Kolide tools become instantly available to pass into streamText or generateText.

Build live security dashboards for your Kolide fleet with the Vercel AI SDK. Stream device status and issues directly into your UI.

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 Vercel AI SDK

Create your Vinkius account to connect Kolide to Vercel AI 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Fleet Health in Real-Time

This MCP server lets you build a UI where security data appears as it's found. Your agent can call `list_kolide_devices` and `list_kolide_issues`, and the AI SDK will stream the results directly into a React table, row by row. There's no loading spinner, just live data. From there, you can make the dashboard interactive. A user clicks a device in the table, and your app instantly calls `get_device_details` and `get_person_details`. The device's specs and owner information populate on screen, field by field, creating a truly responsive experience.

Build Interactive Audit Logs

Forget static log files. You can build a chat interface where an admin asks, "Show me the latest security events." Your agent uses `list_kolide_audit_logs`, and the Vercel AI SDK streams the log entries back as a clean, readable list. This turns auditing into a conversation. The admin can ask a follow-up like, "Tell me more about issue #451," and the agent uses `get_issue_details` to stream back the specifics. It's a faster way to find out what's going on.

Live Fleet Stats for your AI SDK App

Use the `get_kolide_fleet_stats` tool to power a real-time dashboard header. Your Next.js component can show total devices, online count, and open issues, with numbers that update without a page refresh. It gives you an immediate, high-level view of your fleet's health. Because the Vercel AI SDK handles the streaming connection to the MCP Server, you don't have to write any complex fetching logic. You just tell the agent what you need from Kolide and focus on rendering the data as it arrives.

Setup guide

Set up Kolide MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Kolide tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Kolide transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Your agent can call `list_kolide_issues` to get all current problems, then use `get_device_details` for each affected device. The AI SDK streams this combined data right into your UI components, so you can build a live list of at-risk devices and their owners.

Yes. Build a React or Next.js app where an agent uses tools like `get_kolide_fleet_stats` and `list_kolide_issues`. The results stream directly to your components, creating a live dashboard that feels much faster than traditional web apps.

Absolutely. Set up a chat UI where the user's prompt is sent to an agent with the `list_kolide_audit_logs` tool. The AI SDK streams the log entries back one by one, making it feel like you're talking directly to your security data.

Install the `@ai-sdk/mcp` package and point your `createMCPClient` to the Vinkius endpoint token you were given. The Kolide tools become instantly available to pass into `streamText` or `generateText`.

This MCP server only reads your Kolide fleet data, such as device identifiers, OS versions, security check results, and user names. Vinkius isolates every request in an ephemeral sandbox, and your endpoint token is the only key. No data is ever stored.

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