How to Use the Kaseya MCP in OpenAI Agents SDK

Q: How does this setup handle Kaseya VSA 10 agent details and privacy?

The getagentdetails tool reads hardware identifiers, IP addresses, and system statuses. Vinkius runs the MCP Server in an ephemeral V8 Isolate Sandbox. Your connection uses a single endpoint token, which means zero-trust execution where data passes directly to your client without persistent storage.

Manage Kaseya VSA 10 endpoints directly from the OpenAI Agents SDK with built-in guardrails and full execution tracing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kaseya MCP to OpenAI Agents SDK

Create your Vinkius account to connect Kaseya to OpenAI Agents 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 Kaseya with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Auto-Discover Kaseya MCP Server Tools

The `list_agents` and `get_agent_details` tools give your agent immediate visibility into device availability and status. You pass the server instance to the Agent constructor, and the SDK automatically maps these endpoints. Your agent can immediately query active endpoints without writing custom wrapper functions. Execution tracing happens automatically in the OpenAI dashboard. When a specialized troubleshooting agent runs `list_alarms` to check system alerts, you see the exact payload it sent and the response it received. You track every API call and validate agent decisions in production.

Guardrails for IT Automation

The `list_scripts` and `list_workflows` tools require strict boundaries via the MCP server to prevent accidental system changes. The SDK enforces safety constraints before your agent executes any automation workflow. You define the rules, and the framework validates the action against your policy. This setup prevents an overzealous agent from triggering unauthorized updates across your fleet. By combining the `list_groups` tool with strict execution guardrails, you restrict operations to specific machine groups. Your system stays protected while still automating routine maintenance.

Multi-Agent Handoffs for Endpoints

The `list_assets` and `list_organizations` tools let your primary router agent map the infrastructure before handing work to specialists. A triage agent pulls the initial hardware inventory. It then passes the context to a dedicated security agent. That security agent uses `list_audit_logs` to review recent activity for suspicious patterns. Because the framework handles the handoff natively, the second agent picks up exactly where the first left off. You build modular IT teams out of code instead of a single massive prompt.

Setup guide

Set up Kaseya MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Kaseya tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Kaseya tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Kaseya tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Kaseya Agent",
            instructions="You have access to Kaseya tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Kaseya. 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 Kaseya 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 Kaseya MCP in OpenAI Agents SDK

Install openai-agents via pip. Create an MCPServerStreamableHttp instance pointing to your Vinkius endpoint. Pass that into your Agent constructor using the mcp_servers parameter.

Yes. You set cacheToolsList=True in your server configuration. This prevents the agent from re-fetching the schema on every run, which cuts down latency.

The SDK auto-discovers all available endpoints by default. If you only want an agent to read data, you handle that restriction through agent instructions and framework guardrails.

The agent catches the error and can attempt a retry based on your configuration. You can view the exact failure reason inside the OpenAI tracing dashboard.

The get_agent_details tool reads hardware identifiers, IP addresses, and system statuses. Vinkius runs the MCP Server in an ephemeral V8 Isolate Sandbox. Your connection uses a single endpoint token, which means zero-trust execution where data passes directly to your client without persistent storage.

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