How do I set up my HaloPSA API credentials?

Log in as an Administrator, go to **Configuration > Integrations > Halo API**. In 'View Applications', create a new app with the 'Agent' login type and grant the necessary permissions. You will receive your Client ID and Client Secret there.

What are the Resource and Auth URLs?

The Resource URL is typically `https://your-tenant.halopsa.com/api` and the Auth URL is `https://your-tenant.halopsa.com/auth`. Replace 'your-tenant' with your actual HaloPSA instance name.

Can I perform actions on tickets, like changing status?

Yes! Use the `perform_ticket_action` tool by providing the ticket ID and the specific action ID configured in your Halo instance. You can also add an optional note.

Is the integration secure?

Yes, it uses industry-standard OAuth2 Client Credentials flow. Your credentials are encrypted and stored securely within the Vinkius Cloud infrastructure.

HaloPSA MCP Server for OpenAI Agents SDK 11 tools — connect in under 2 minutes

Name: HaloPSA
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 11 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect HaloPSA through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.

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 agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="HaloPSA Assistant",
            instructions=(
                "You help users interact with HaloPSA. "
                "You have access to 11 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from HaloPSA"
        )
        print(result.final_output)

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 HaloPSA MCP Server

Connect your HaloPSA instance to any AI agent and take full control of your service desk and PSA workflows through natural conversation.

The OpenAI Agents SDK auto-discovers all 11 tools from HaloPSA through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries HaloPSA, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

What you can do

Ticket Management — List all tickets, retrieve detailed information, and create new support requests effortlessly.
Client & User Oversight — Access lists of clients (customers) and users defined in your system to ensure data accuracy.
Asset Tracking — Monitor the hardware and software assets managed within HaloPSA.
Team Coordination — Browse your organizational teams and sites to facilitate better resource allocation.
Financial Insights — Retrieve lists of invoices and customer contracts for quick status checks.
Action Execution — Perform updates on tickets, add internal notes, or change statuses directly from the chat.

The HaloPSA MCP Server exposes 11 tools through the Vinkius. Connect it to OpenAI Agents SDK 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 HaloPSA to OpenAI Agents SDK via MCP

Follow these steps to integrate the HaloPSA MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 11 tools from HaloPSA

Why Use OpenAI Agents SDK with the HaloPSA MCP Server

OpenAI Agents SDK provides unique advantages when paired with HaloPSA through the Model Context Protocol.

Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

HaloPSA + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the HaloPSA MCP Server delivers measurable value.

Automated workflows: build agents that query HaloPSA, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents — one queries HaloPSA, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through HaloPSA tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query HaloPSA to resolve tickets, look up records, and update statuses without human intervention

HaloPSA MCP Tools for OpenAI Agents SDK (11)

These 11 tools become available when you connect HaloPSA to OpenAI Agents SDK via MCP:

create_ticket

Create a new ticket in HaloPSA

get_ticket

Get detailed information about a specific ticket

list_assets

List all assets defined in HaloPSA

list_clients

List all clients (customers) in HaloPSA

list_contracts

List all customer contracts

list_invoices

List all invoices in HaloPSA

list_sites

List all sites/locations

list_teams

List all teams configured in the service desk

list_tickets

List all tickets in HaloPSA

list_users

List all users in the HaloPSA instance

perform_ticket_action

Perform an action on a ticket (e.g., add note, change status)

Example Prompts for HaloPSA in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with HaloPSA immediately.

"List all open tickets assigned to me."

"Add an internal note to ticket ID 1021: 'Waiting for vendor feedback'."

"Show me the asset list for Client 'Acme Corp'."

Troubleshooting HaloPSA MCP Server with OpenAI Agents SDK

Common issues when connecting HaloPSA to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

HaloPSA + OpenAI Agents SDK FAQ

Common questions about integrating HaloPSA MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.