Where do I find my Kolide API Token?

Log in to the Kolide dashboard, navigate to **Settings** in the bottom left, and select the **API** tab to generate a token.

Can I see hardware details of a device?

Yes, the `get_device_details` tool returns hardware specifications along with security data.

Does this support multi-tenant accounts?

The API key is typically scoped to a specific organization. Ensure you are using the token for the desired fleet.

Kolide MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Kolide
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Kolide through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Kolide "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Kolide?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Kolide MCP Server

Connect your AI agent to Kolide to get full visibility into your organization's fleet security and device health.

Pydantic AI validates every Kolide tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

Key Features

Fleet Inventory — List all managed devices and their high-level security status
Issue Tracking — Monitor active security vulnerabilities and misconfigurations across your fleet
People & Ownership — See which users are associated with which devices and their individual compliance state
Security Checks — Audit available security checks and dive into specific failure conditions
Audit Logs — Access a chronological history of administrative and security events

How to setup

1. Subscribe to this server
2. Log in to Kolide, go to Settings > API, and generate a Bearer Token
3. Enter your token in the configuration
4. Start auditing your fleet via natural language

The Kolide MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Kolide to Pydantic AI via MCP

Follow these steps to integrate the Kolide MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Kolide with type-safe schemas

Why Use Pydantic AI with the Kolide MCP Server

Pydantic AI provides unique advantages when paired with Kolide through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Kolide integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Kolide connection logic from agent behavior for testable, maintainable code

Kolide + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Kolide MCP Server delivers measurable value.

Type-safe data pipelines: query Kolide with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Kolide tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Kolide and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Kolide responses and write comprehensive agent tests

Kolide MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Kolide to Pydantic AI via MCP:

get_check_details

Get details for a specific check

get_device_details

Get details for a specific device

get_issue_details

Get details for a specific security issue

get_kolide_fleet_stats

g., total devices, online status, issue count). Get high-level fleet statistics

get_person_details

Get details for a specific person

list_kolide_audit_logs

List fleet audit logs

list_kolide_checks

List all available security checks

list_kolide_devices

Use this to audit fleet security posture and identify individual device IDs. List all devices in the fleet

list_kolide_issues

List security issues across the fleet

list_kolide_people

List people/users managed in Kolide

Example Prompts for Kolide in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Kolide immediately.

"List all devices currently online in Kolide"

"What are the most common security issues in my fleet?"

"Show fleet statistics for today"

Troubleshooting Kolide MCP Server with Pydantic AI

Common issues when connecting Kolide to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Kolide + Pydantic AI FAQ

Common questions about integrating Kolide MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Kolide MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.