AI Agent Integration

Model Context Protocol (MCP) Server

HVACStandby provides an automated MCP server for external AI agents, dispatch copilots, and autonomous schedulers.

Discovery & Endpoints

Discovery Manifest: GET /.well-known/mcp.json
JSON-RPC 2.0 Endpoint: POST /api/mcp
Documentation Page: GET /mcp
Context Brief: GET /llms.txt

Available Tools & inputSchema Definitions

`get_dispatch_state`

Get current HVAC technician dispatch board state, technicians, scheduled jobs, and standby roster.

inputSchema (JSON Schema):

{
  "type": "object",
  "properties": {
    "day": {
      "type": "string",
      "description": "Optional ISO date string (YYYY-MM-DD)"
    },
    "techId": {
      "type": "string",
      "description": "Optional technician ID"
    }
  }
}

`evaluate_standby_backfill`

Evaluate and rank standby candidates to backfill a cancelled HVAC slot by proximity, maintenance tier, and system replacement bonus.

inputSchema (JSON Schema):

{
  "type": "object",
  "properties": {
    "slotStart": {
      "type": "string",
      "description": "ISO datetime of the open slot"
    },
    "targetZip": {
      "type": "string",
      "description": "Target ZIP code of the open slot"
    },
    "cancelledJobId": {
      "type": "string",
      "description": "Optional ID of cancelled job"
    }
  }
}

JSON-RPC 2.0 Sample Call

Sample tools/call request to evaluate a standby window:

curl -X POST https://hvacstandby.com/api/mcp \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
      "name": "evaluate_standby_backfill",
      "arguments": {
        "slotStart": "2026-10-29T10:00:00",
        "targetZip": "75001"
      }
    }
  }'

← Back to HVACStandby Home · Comparison · Pricing