How to Use the HaloPSA MCP in OpenAI Agents SDK

Q: Can the agent assign tickets to specific service desk teams?

Yes. Your agent uses listteams to pull the active group list from your instance, then matches the ticket metadata to the right team ID. It then runs performticketaction to update the assignment, ensuring the right engineers get notified.

Q: Is my HaloPSA ticket and client data safe with this setup?

Your service desk data, including ticket descriptions from getticket and client details from listclients, stays secure inside the Vinkius sandboxed environment. We use ephemeral V8 isolates to run the connection, meaning no data is written to persistent storage or used to train public models.

Run guardrail-protected OpenAI Agents SDK workflows via our MCP Server to update tickets and query assets.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HaloPSA MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe ticket updates with built-in guardrails

OpenAI Agents SDK uses this MCP Server to build multi-agent setups that don't run wild. When your agent decides to update a customer issue, the SDK runs validation checks before calling `perform_ticket_action`. You get clean ticket updates without worrying about an agent writing garbage into your production database. By calling the `get_ticket` tool, it pulls current status, validates it against your internal rules, and only then pushes the edit. Your service desk stays clean and SLA metrics remain accurate.

Automated dispatch using OpenAI Agents SDK

By connecting this MCP Server to your runtimes, triage workflows run automatically when your agent uses `list_tickets` to scan incoming queues. The SDK handles agent handoffs, passing the ticket context from a triage agent to a specialized technical agent. You don't have to manually route issues anymore. The agent looks up team availability with `list_teams` and matches it against the ticket requirements. Once a match is found, it executes `perform_ticket_action` to assign the work. Your team starts their day with a pre-sorted queue instead of a chaotic inbox.

Fast customer context lookups

Your AI client uses `list_clients` to pull customer context before promising a fix. This integration exposes both client profiles and `list_contracts` directly to your model's context window. The agent instantly knows if a client has an active agreement or if they are out of contract. If a client files a request for an untracked device, the agent runs `list_assets` to match the hardware. This stops your team from working on unbilled gear. It puts all billing and asset data right where the agent can act on it.

Setup guide

Set up HaloPSA 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 HaloPSA tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate HaloPSA 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="HaloPSA Agent",
            instructions="You have access to HaloPSA 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 HaloPSA. 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 HaloPSA 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 HaloPSA MCP in OpenAI Agents SDK

Install the package using pip, then initialize the streamable HTTP client pointing to your Vinkius endpoint. Pass this server instance into your Agent constructor's server list. The agent automatically discovers tools like `list_tickets` and `create_ticket` without manual mapping.

Yes, you control this at the agent level or via your Vinkius credentials. If you want a specific agent to only read data, you can limit its scope so it never calls write tools like `create_ticket` or `perform_ticket_action`. This keeps your service desk safe from accidental modifications.

The SDK relies on the underlying HTTP client to manage requests. If you run heavy loops with `list_invoices` or `list_users`, the connection handles standard backoff. You should also set your configuration to cache tools to prevent redundant schema lookups.

Yes. Your agent uses `list_teams` to pull the active group list from your instance, then matches the ticket metadata to the right team ID. It then runs `perform_ticket_action` to update the assignment, ensuring the right engineers get notified.

Your service desk data, including ticket descriptions from `get_ticket` and client details from `list_clients`, stays secure inside the Vinkius sandboxed environment. We use ephemeral V8 isolates to run the connection, meaning no data is written to persistent storage or used to train public models.

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