Honeywell Forge MCP for AI. Cross-reference security events with building metrics.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Connect to your AI in seconds.
Honeywell Forge MCP connects your AI agent to facility infrastructure. Use this MCP to pull real-time data on security alarms, track energy usage across specific zones, check door status, and audit entire buildings from one place.
What your AI can do
Acknowledge alarm
Marks an active alarm as reviewed by a human team member for incident tracking and compliance logs.
Get alarms
Retrieves a list of all current or historical security, fire, or HVAC alarms across one or more buildings.
Get building details
Returns deep metadata for a site, including its floor plans, linked access control systems, and energy targets.
Get a real-time list of alarms across buildings or specific sites.
Check the current open/closed, locked/unlocked status for any door or gate.
Retrieve energy consumption data, including total usage and cost estimates by subsystem.
Pull detailed information on a site's HVAC zones, floor plans, and linked systems.
Remotely lock or unlock specific doors for security or maintenance purposes.
Ask an AI about this
Honeywell Forge: 11 Tools Available
These tools let you pull specific, operational data from a facility's infrastructure, covering everything from basic alarm checks to complex energy consumption reports.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Honeywell Forge on VinkiusAcknowledge Alarm
Marks an active alarm as reviewed by a human team member for incident tracking and compliance logs.
Get Alarms
Retrieves a list of all current or historical security, fire, or HVAC alarms across...
Get Building Details
Returns deep metadata for a site, including its floor plans, linked access control...
Get Door Status
Provides a read-only snapshot of whether a specific door is open/closed and...
Get Energy Usage
Calculates aggregated power consumption data, including total cost estimates and...
Get Temperature Data
Pulls sensor readings for temperature, humidity, and HVAC equipment status for a specific zone.
List Access Points
Lists every physical entry device (doors, gates) in a building along with its current lock state and assigned access level.
List Buildings
Provides a list of all registered buildings, giving you the ID needed to run any...
List Video Feeds
Finds available cameras and NVR channels, listing their location, stream URLs, and...
Lock Door
Engages the locking mechanism on a specified door or access point immediately.
Unlock Door
Disengages the lock on a specific door, allowing free movement until it's explicitly...
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Claude AI
Open Claude Settings
Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
Add Custom Connector
Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:
https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp
Replace [YOUR_TOKEN_HERE] with your token
from cloud.vinkius.com. For OAuth-protected servers, expand
Advanced settings to add credentials.
Start a conversation
Open a new chat. The Honeywell Forge integration is available immediately — no restart needed.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Honeywell Forge, then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,100+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 11 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
The daily pain of manual facility checks is endless.
Today, reconciling an incident means logging into the alarm panel to check for open faults, then switching over to the energy dashboard to see if usage spiked at the same time. You copy down a dozen IDs; you cross-reference timestamps manually; and finally, you call building maintenance to confirm the physical status of the door.
With this MCP, your agent handles that whole sequence in one query. It pulls together data from multiple sources—like checking get_alarms against list_access_points and then querying get_door_status—and presents a single narrative report. You just ask for 'the story,' and you get it.
Control Site Access with lock_door
Before, if you needed to secure the building at night, you'd have to walk the perimeter or manually log into dozens of subsystems and trigger locks one by one. It's slow, tedious work that requires knowing every single access point ID.
Now, after running list_access_points to gather all IDs for a zone, your agent executes lock_door across the board in seconds. You enforce security policy instantly—no more missed doors.
What your AI can actually do with this
Managing a large site means juggling multiple systems: the HVAC controls, access badge logs, fire alarms, and utility meters. This connector brings all that operational intelligence together for your AI client. You can ask it to cross-reference an alarm event with the building's energy consumption data, or check if a door was forced open right before a temperature spike.
It lets you get a full picture of what happened—not just where the fault is, but why it matters to operations and compliance. This type of centralized control means your agent can handle complex incident reviews that used to take an entire afternoon in multiple dashboards. You access this functionality through Vinkius, connecting your favorite AI client directly to facility-grade tools.
019d75b2-9a6e-7105-b5d0-a0d50aaa8661 
Here's how it actually works
The bottom line is: Instead of logging into five different vendor portals, you ask your AI client one question and get the full answer.
First, tell your AI client which building you're focused on using the list_buildings tool to get a unique ID.
Next, prompt it with the specific data points needed—maybe checking the temperature data or running through available video feeds for that site.
Finally, your agent returns structured reports, allowing you to see everything from alarm history and energy metrics to current door status.
Who is this actually for?
Facility Managers, Security Directors, and Operations Engineers. If you're tired of manually clicking through separate dashboards to reconcile a security alarm with an energy spike, this is for you.
Manages recurring maintenance tasks, checking the get_temperature_data against setpoints and running reports on total kWh usage.
Triages physical incidents by listing access points and using the acknowledge_alarm tool to track which security teams have seen a breach event.
Validates system state before making changes, like checking get_door_status or pulling detailed building information with get_building_details.
What Changes When You Connect
Immediate incident response: Instead of sifting through logs, you can call get_alarms and immediately use acknowledge_alarm to update the audit trail. It tells your agent that a human team saw it, which is critical for compliance.
Cross-System Auditing: You can pair list_access_points with get_door_status. Your agent verifies if a security alarm matches a physical door being forced open or left unlocked.
Efficiency in Reporting: The get_energy_usage tool provides cost breakdowns, letting you quickly identify which subsystem (like HVAC) is causing demand peaks without manually pulling utility reports.
Deep Site Awareness: By running get_building_details first, your agent knows the context—the specific zones and subsystems—before checking things like list_video_feeds or getting temperature data. It adds necessary structure.
Remote Control Capability: Need to secure a site after hours? You can use lock_door on multiple points, confirming the exact access point ID via list_access_points first.
See it in action
Investigating an Overnight Alarm Spike
The operations engineer runs get_alarms and finds a series of door faults. They then use get_building_details to understand the zone layout, check list_access_points for related doors, and finally run get_door_status on those specific points to see if they were physically open or just reported as such.
Validating HVAC Maintenance
A facilities manager notices a complaint about cold air. They use get_temperature_data to pull the zone readings, compare them against the setpoint targets listed in get_building_details, and if needed, they can send alerts based on those metrics.
Securing a Site After Hours
The security team needs to lock down. They use list_buildings for the site ID, then call list_access_points to get all relevant IDs, and finally execute lock_door on every point in that area.
Analyzing Video Footage Correlated with Faults
After a major incident, an agent uses get_alarms to find the time of the breach. They then use list_video_feeds to pull all camera streams near that alarm's source device for forensic review.
The honest tradeoffs
Treating all data as equal
Asking your agent simply, 'What is wrong with the building?' This results in a massive block of unrelated text mixing alarm IDs, energy kW ratings, and temperature degrees.
Don't ask for everything. Break it down: First, use list_buildings to scope the request. Then, query get_alarms or get_energy_usage specifically. Always define the boundaries before asking for data.
Ignoring required IDs
Attempting to lock a door using only its name, 'Main Entrance.' The system fails because it doesn't know which specific access point ID you mean.
Always start with list_access_points. Get the precise access point ID first; then, use that confirmed ID when calling lock_door or unlock_door to guarantee accuracy.
Mixing live status and history
Asking for 'all door information.' This mixes a real-time snapshot (get_door_status) with historical audit logs, resulting in confusing data.
Separate your calls. Use get_alarms for historical incidents, but use get_door_status or list_access_points when you need the current physical state.
When It Fits, When It Doesn't
Use this MCP if your job requires correlating multiple types of data: security events with environmental conditions, or energy metrics with physical access. You need to know why an alarm triggered—was it a door left open (get_door_status), which in turn caused HVAC issues (get_temperature_data)? Don't use this if you only need one piece of information; for example, just listing all cameras requires only list_video_feeds. If you are building complex workflows that require knowing the site ID first, start with list_buildings. Never rely on a single tool alone; its value comes from stitching together data points like get_alarms and get_energy_usage.
Questions you might have
How do I find out what sensors are available using get_temperature_data? +
get_temperature_data only provides sensor readings for a specific, pre-defined zone. To see what zones exist first, run get_building_details to review the full list of HVAC zones associated with your site.
Can I use list_buildings before running other tools? +
Yes, it's smart practice. list_buildings gives you all available building IDs and names; this ID is required input for almost every other tool, including get_alarms or get_energy_usage.
What is the difference between get_door_status and list_access_points? +
list_access_points gives you a full inventory of all entry points and their configured access levels. get_door_status only provides the real-time, point-in-time physical status (open/closed) for one specific door.
How do I check video feeds with list_video_feeds? +
list_video_feeds pulls metadata like camera name and stream URL. You must use this tool first to discover which cameras are available, as it provides the necessary IDs for viewing or correlation.
If I run `acknowledge_alarm` while the system still has an active fault, what does that mean for compliance records? +
Acknowledging an alarm simply updates its status; it doesn't clear the physical condition. This change is crucial because it logs exactly when human operations staff reviewed the issue, which satisfies compliance and incident tracking requirements.
When should I use `list_access_points` before running a command like `lock_door`? +
You must run list_access_points first to confirm the specific ID of the door. This prevents accidental commands and ensures you are locking or unlocking the correct physical access surface on site.
How do I scope my search when using `get_alarms` across a massive campus? +
You can filter results by passing the specific building ID. This narrows down the output immediately, allowing you to triage active alarms or audit historical events at a single, defined site.
Why is it best practice to run `get_building_details` before checking energy usage with `get_energy_usage`? +
This MCP provides deep metadata like HVAC zones and operating schedules. Getting the building details first gives context, helping you understand why certain energy consumption patterns exist or when systems are supposed to be running.
We've already built the connector for Honeywell Forge. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 11 tools are live and waiting.
You're up and running in seconds.
Gemini Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.