How to Use the Honeywell Forge MCP in OpenAI Agents SDK

Q: How do I connect Honeywell Forge to the OpenAI Agents SDK?

Run pip install openai-agents. Create an MCPServerStreamableHttp instance with your MCP endpoint URL. Pass it to your Agent constructor in the mcpservers array.

Q: Can my OpenAI Agents SDK setup automatically discover Honeywell Forge tools?

Yes. The SDK auto-discovers all 11 tools. Set cacheToolsList=True to speed up the initialization time.

Q: Does the agent know if a door is already open?

It checks getdoorstatus first. The response tells the agent if the door is held open or forced.

Control building security and HVAC systems directly from your OpenAI Agents SDK workflows via MCP.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Honeywell Forge MCP to OpenAI Agents SDK

Create your Vinkius account to connect Honeywell Forge 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 Honeywell Forge with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Triage Active Incidents

`get_alarms` pulls the exact severity and source device for active incidents. Your agent reads the fire and life safety warnings. It uses the built-in guardrails to verify the event before taking action. Look, if it is a routine fault, the agent runs `acknowledge_alarm` to update the audit log. This records the human review without clearing the underlying condition. You track exactly what the system handled.

Secure Facilities with this MCP Server

`get_building_details` hands this MCP Server the full floor plan and linked access control subsystems. Your agent maps the layout. Then it uses `list_access_points` to find the exact turnstiles and gates. When you need a lockdown, the agent executes `lock_door` under your predefined safety constraints. The door immediately engages its locking mechanism. Only authorized credential holders can override it via badge access.

Optimize Energy Consumption

`get_energy_usage` retrieves the raw kWh consumption and demand peaks for specific sites. Your specialized analytics agent takes that data. It compares the metrics against the established energy targets. The agent then runs `get_temperature_data` to check compressor status and valve positions. It finds zones wasting power on cooling empty rooms. You get a complete trace of the agent's logic in the OpenAI dashboard.

Setup guide

Set up Honeywell Forge 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 Honeywell Forge tools at runtime.
3

Create your Agent

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

Run the agent

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

Run `pip install openai-agents`. Create an `MCPServerStreamableHttp` instance with your MCP endpoint URL. Pass it to your Agent constructor in the `mcp_servers` array.

Yes. The SDK auto-discovers all 11 tools. Set `cacheToolsList=True` to speed up the initialization time.

Use the built-in guardrails. You define strict validation rules that the agent must pass before it executes the `lock_door` command.

It checks `get_door_status` first. The response tells the agent if the door is held open or forced.

The MCP architecture runs a zero-trust V8 Isolate Sandbox. The server reads zone temperatures and fan speeds ephemerally. Nothing writes to disk, and the token expires immediately.

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