Plug HVAC into Claude, ChatGPT, and any MCP agent.

Returns every brand the agent can read or control. Useful when a Claude agent is starting fresh and needs to know what equipment it can integrate.

{ category?: "HVAC" | "HomeAutomation" | "BMS"; status?: "supported" | "beta" | "planned" }

{ brands: { slug; name; category; protocols; status }[] }

list_brands({ category: "HVAC", status: "supported" })

Resolves a brand slug to its device families, supported points, and protocol matrix. Use it before deciding whether to attempt a control call against a specific brand.

{ slug: string }

{ brand; deviceFamilies; capabilities; protocols }

get_brand_capabilities({ slug: "daikin" })

Each site is a parent scope. Faults, energy roll-ups, and device queries are typically scoped to a site.

{ limit?: number; cursor?: string }

{ sites: Site[]; nextCursor?: string }

list_sites({})

Normalized across brands. Claude can ask "what is the conference-room VRV doing?" and get a JSON it can reason over without learning per-brand semantics.

{ deviceId: string }

{ temperature; humidity; setpoint; mode; fanSpeed; status; readAt }

read_device_state({ deviceId: "site-3-vrv-conf-12" })

Returns time-series data for the requested points. Resolution is auto-selected by window size; ask for explicit resolution if you need it.

{ deviceId; points: string[]; from: ISO8601; to: ISO8601; resolution?: "1m"|"5m"|"1h"|"1d" }

{ points: { name; samples: [t, v][] }[] }

read_device_history({ deviceId: "rtu-7", points: ["temperature","setpoint"], from: "2026-05-27T00:00:00Z", to: "2026-05-27T23:59:59Z" })

Gated by per-device write scope AND your site safety interlocks. Every write is recorded with the calling agent, before/after, reason, and outcome.

{ deviceId; value: number; reason?: string }

{ ok; before; after; appliedAt; auditId }

set_device_setpoint({ deviceId: "rtu-7", value: 72, reason: "Pre-cool for 9am occupancy" })

Bounded by the device's capabilities. The MCP server validates the mode is supported before calling the brand API; on mismatch returns the allowed mode list.

{ deviceId; mode: "heat"|"cool"|"auto"|"off"|"fan"|"dry" }

{ ok; before; after; appliedAt; auditId }

set_device_mode({ deviceId: "rtu-7", mode: "cool" })

Same data that powers /technician-copilot. Use it to triage what needs attention right now, or to compose a daily site-summary email.

{ siteId?: string; severity?: "info"|"warning"|"critical" }

{ faults: Fault[]; nextCursor? }

list_active_faults({ severity: "critical" })

Resolves a brand + code to its category, plain-English meaning, severity, and first-checks. The dataset that powers /brands/<slug> fault-code tables, callable from any MCP-aware agent.

{ brand: string; code: string }

{ brand; code; category; meaning; severity; suggestedAction }

explain_fault_code({ brand: "daikin", code: "U4" })

Stops further notifications for the configured cooldown. Acknowledgement is audit-logged with the calling agent.

{ faultId: string; note?: string }

{ ok; acknowledgedAt; by }

acknowledge_fault({ faultId: "f-83210", note: "Tech dispatched, ETA 14:00" })

Aggregates per-device telemetry into a single site energy series. Same series the M&V / IPMVP report generator uses — your numbers and the report's match.

{ siteId; from: ISO8601; to: ISO8601 }

{ kWh; peakKW; demandKW; samples: [t, kW][] }

site_energy_summary({ siteId: "store-42", from: "2026-05-01T00:00:00Z", to: "2026-05-31T23:59:59Z" })

Pure-function helper for agents reasoning about HVAC efficiency levers. Saves the LLM from re-deriving the Tetens/Stull approximations every time it wants to talk about enthalpy.

{ tempF: number; rh: number; pressureKPa?: number }

{ wetBulbF; dewPointF; enthalpyBtuPerLb; humidityRatio }

compute_psychrometrics({ tempF: 88, rh: 62 })