How to Use the Hudu MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK connect to Hudu?

You instantiate an MCPServerStreamableHttp object with your Vinkius MCP endpoint URL. Pass this server instance to your Agent constructor. The tools are discovered automatically, so you don't need to define them manually.

Q: How do I list all assets for one specific client in Hudu using the OpenAI Agents SDK?

Your agent would first use listcompanies to find the correct company ID. Then, it calls listassets and passes that company ID as a parameter. The agent figures this out from the tool's schema.

Build production MSP agents with the OpenAI Agents SDK to manage Hudu assets and passwords with built-in guardrails and tracing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hudu MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Companies and Assets

Your agent can create new client records and track their hardware. Use `create_company` to onboard a new customer, then populate their inventory with `create_asset` for every server, firewall, and workstation. It's all logged in the OpenAI dashboard. When you need to see what's deployed, the agent calls `list_companies` to get a full client roster. From there, it can run `list_assets` filtered by a company ID to pull a specific customer's hardware list. No more manual lookups in the Hudu UI.

Access Documentation and Procedures

Stop digging through wikis during an outage. An agent can pull critical info directly from Hudu's knowledge base using `list_articles` and `get_article`. It finds the right document based on the incident context. For step-by-step instructions, the agent uses `get_procedure` to fetch the exact runbook. This means your response team gets consistent, approved instructions every time, without wasting seconds searching. The MCP connection acts as a direct bridge to your documentation.

Secure Hudu Passwords with OpenAI Agents SDK

This is where the OpenAI guardrails really matter. Your agent can fetch credentials using `get_password` or `list_passwords` for a specific company. The framework lets you require human-in-the-loop approval before the agent actually uses the password. You get full visibility. Every call is traced, so you have an audit trail of which agent accessed what credential and when. This isn't just automation; it's accountable automation for your most sensitive data.

Setup guide

Set up Hudu 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 Hudu tools at runtime.
3

Create your Agent

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

Run the agent

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

You instantiate an `MCPServerStreamableHttp` object with your Vinkius MCP endpoint URL. Pass this server instance to your Agent constructor. The tools are discovered automatically, so you don't need to define them manually.

Yes. The OpenAI Agents SDK framework has built-in guardrails. You can configure it to require human approval for any tool call, especially destructive ones like `create_asset` or `create_company`.

Yes, if you use the safety features. The SDK is designed for this. You can force a confirmation step before any `get_password` call is executed, giving a human final say before a credential is exposed.

Your agent would first use `list_companies` to find the correct company ID. Then, it calls `list_assets` and passes that company ID as a parameter. The agent figures this out from the tool's schema.

It only touches the data your agent asks for. This includes company names, asset details, knowledge base articles, procedures, and encrypted passwords. Your Vinkius endpoint token secures the connection, and all data is processed ephemerally within a sandbox.

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