# Honeywell Forge MCP > 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. ## Overview - **Category:** industry-titans - **Price:** Free ## Description 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. ## Tools ### 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_door_status Provides a read-only snapshot of whether a specific door is open/closed and locked/unlocked right now. ### get_energy_usage Calculates aggregated power consumption data, including total cost estimates and breakdowns by HVAC or lighting systems. ### 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 other operation on site. ### list_video_feeds Finds available cameras and NVR channels, listing their location, stream URLs, and current online status. ### 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 relocked. ## Capabilities ### Triage Active Incidents Get a real-time list of alarms across buildings or specific sites. ### Audit Physical Access Points Check the current open/closed, locked/unlocked status for any door or gate. ### Measure Operational Costs Retrieve energy consumption data, including total usage and cost estimates by subsystem. ### View Building Metadata Pull detailed information on a site's HVAC zones, floor plans, and linked systems. ### Control Access Status Remotely lock or unlock specific doors for security or maintenance purposes. ## Use Cases ### 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. ## Benefits - 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. ## How It 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. 1. First, tell your AI client which building you're focused on using the list_buildings tool to get a unique ID. 2. Next, prompt it with the specific data points needed—maybe checking the temperature data or running through available video feeds for that site. 3. Finally, your agent returns structured reports, allowing you to see everything from alarm history and energy metrics to current door status. ## Frequently Asked Questions **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.