How to Use the Honeywell Forge MCP in LangChain

Q: How do I connect Honeywell Forge to LangChain?

Install the langchain-mcp-adapters package. Initialize a MultiServerMCPClient with your endpoint URL and pass the resulting tools to your ReAct agent.

Q: Can LangChain agents control physical doors in Honeywell Forge?

Yes. Your agent can execute lockdoor and unlockdoor if you grant it the right permissions. Always implement human-in-the-loop approval for physical security commands.

Q: How do I handle multi-building queries?

Write a chain that first calls listbuildings to get the site IDs. Pass those IDs into a map-reduce chain that queries getenergyusage for each location.

Build multi-step building automation pipelines with LangChain. Connect your agents directly to live HVAC and security data.

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 LangChain

Create your Vinkius account to connect Honeywell Forge to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build incident response chains with LangChain

Your ReAct agents need live data to make decisions. When a security event fires, you don't want a static alert. You want an agent that pulls the `get_alarms` feed, identifies the trigger, and immediately runs `list_video_feeds` to find the nearest camera. That output becomes the input for the next step. The agent checks `get_door_status` to see if the perimeter was breached. If the door is forced open, the chain executes a `lock_door` command via the MCP Server to secure the adjacent zones. Every tool call gets tracked in LangSmith for full observability.

Automate energy audits across facilities

Facility managers spend hours compiling consumption reports. You can wire up a LangChain agent to do this automatically. It starts by pulling the portfolio with `list_buildings`, then iterates through each site using `get_building_details` to grab the baseline energy targets. Next, the agent queries `get_energy_usage` for the actual consumption numbers and `get_temperature_data` to check HVAC performance. It compares the two, flags zones wasting power, and outputs a formatted markdown report. You get the final analysis without manually pulling a single spreadsheet.

Handle complex HVAC diagnostics

Thermal comfort complaints usually require a technician to check multiple systems. An agent connected to this MCP server handles the initial triage. It runs `get_temperature_data` to check the current zone setpoints and valve positions. If the system shows a fault, the agent can pull `get_alarms` to see if a compressor tripped. When it identifies a known issue, it uses `acknowledge_alarm` to log that the operations team is aware. The chain finishes by generating a work order with exact diagnostic data attached.

Setup guide

Set up Honeywell Forge MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Honeywell Forge tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "honeywell-forge-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Honeywell Forge transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Install the `langchain-mcp-adapters` package. Initialize a `MultiServerMCPClient` with your endpoint URL and pass the resulting tools to your ReAct agent.

Yes. Your agent can execute `lock_door` and `unlock_door` if you grant it the right permissions. Always implement human-in-the-loop approval for physical security commands.

It tracks everything. You get full visibility into the exact payload sent to the MCP Server and the JSON response returned by the building management system.

Write a chain that first calls `list_buildings` to get the site IDs. Pass those IDs into a map-reduce chain that queries `get_energy_usage` for each location.

The MCP protocol operates on a zero-trust model. When your agent pulls HVAC setpoints or door access logs, that data stays in your local runtime. The V8 isolate sandbox tears down immediately after the connection drops.

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