How to Use the Kolide MCP in Pydantic AI

Strictly typed Kolide data for Pydantic AI. Ensure your fleet security logic never fails due to unexpected API responses.

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 Pydantic AI

Create your Vinkius account to connect Kolide to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe fleet security checks

Every response from `list_kolide_checks` is validated against your Pydantic models at runtime. This prevents your agent from processing corrupted data or hallucinated fields when auditing your fleet. If the API returns an unexpected structure, the agent stops immediately. This keeps your security logic predictable and reliable.

Reliable device and issue reporting

Query `list_kolide_issues` and `get_issue_details` with full confidence that the data matches your expected schema. Your agent will only act on data that passes your strict validation rules. This makes it easy to write robust logic that handles security findings without worrying about unexpected JSON keys or missing values.

Validated fleet statistics

Use `get_kolide_fleet_stats` to get a clean, validated snapshot of your fleet health. Because Pydantic AI enforces your data models, you know exactly what the numbers represent before your agent makes a decision. This is essential for automated workflows where you need to trust the data coming from your security tools implicitly.

Setup guide

Set up Kolide MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "kolide-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Kolide tools.",
)

result = await agent.run("List recent Kolide transactions")
print(result.output)

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 Pydantic AI

Install the MCP toolset package and initialize it with your server URL. You can then add it directly to your agent's list of tools.

Yes, every tool response is checked against your defined models. If the data returned by `get_device_details` doesn't match, the agent will throw a validation error.

Yes, the MCP server is model-agnostic. Whether you use OpenAI, Anthropic, or local models, the Pydantic validation handles the data consistency.

Validation happens at the agent level within your Python runtime. This ensures that your local code is always the final arbiter of data quality.

Pydantic AI will catch the missing field during validation. You can define your models to handle these cases gracefully or force the agent to re-query.

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