Connect your AI assistant (Claude, ChatGPT, Copilot, Perplexity, Cursor, or any MCP-compatible tool) directly to your Caddis machine data. Once connected, you can ask questions about your shop floor in plain language and get answers grounded in your real equipment data — no dashboards, no exports, no scripts.

Note: If you previously set up the Caddis MCP Server using a username/password and an npx or Docker install, that method is deprecated and no longer works. Follow the steps below to switch to the new hosted server.

What You'll Need

Nothing to install. No passwords to enter into a config file.

Step 1: Add the Caddis Server to Your AI Tool

If you use Claude Code:

Open your terminal and run:

Claude Code (CLI)
bash 
claude mcp add caddis --transport http https://api.lcm2m.com/mcp
Claude Desktop, Cursor & Similar (JSON Config)
json 
{
  "mcpServers": {
    "caddis": {
      "url": "https://api.lcm2m.com/mcp"
    }
  }
}

‍

If you use ChatGPT, Copilot, or Perplexity: these tools support connecting to remote MCP servers through their own connector or plugin settings (naming varies by tool — look for "Connectors," "Plugins," or "MCP Servers" in settings). Add the server URL: https://api.lcm2m.com/mcp

Using a different tool (Windsurf, VS Code, Zed, Continue, Cline, etc.)? Look for a setting like "Remote MCP Server" or "HTTP MCP Server" and enter the same URL.

Step 2: Restart Your AI Tool

Fully quit and reopen the app (or refresh the page for web-based tools like ChatGPT or Perplexity) so it picks up the new connection.

Step 3: Sign In

The first time you ask your AI tool something that needs Caddis data, a browser window will open asking you to log in with your LCM2M account. Sign in once — after that, you're connected.

That's it. No environment variables, no company ID to look up, no password to store.

What You Can Ask

Once connected, try prompts like:

All data returned is read-only — the assistant can view your equipment, runs, telemetry, and alarms, but can't change anything in your Caddis account.

Available Tools

All tools are read-only and prefixed with caddis_. Each maps directly to a VM2M API route.

Category Tool Description
Company caddis_get_company Returns company-level details for your LCM2M account
Devices caddis_list_devices Lists all connected devices
Devices caddis_get_device Returns details for a specific device
Equipment caddis_list_equipment Lists all equipment in your account
Equipment caddis_get_equipment Returns details for a specific piece of equipment
Equipment caddis_get_equipment_utilization Returns utilization metrics for a machine
Equipment caddis_get_equipment_schedule Returns the production schedule for a machine
Equipment caddis_get_equipment_cycles Returns cycle data for a machine over a time range
Equipment caddis_get_equipment_statuslogs Returns status change logs (running, idle, off)
Equipment caddis_get_equipment_telemetry Returns raw telemetry data from a machine
Equipment caddis_get_equipment_shift_history Returns shift-level production history
Equipment caddis_list_equipment_excessive_downtimes Lists excessive downtime events for equipment
Equipment caddis_get_equipment_excessive_downtime Returns details for a specific excessive downtime event
Org units caddis_get_org_unit Returns details for an org unit (line, cell, plant)
Org units caddis_get_org_unit_schedule Returns the schedule for an org unit
Org units caddis_list_org_unit_excessive_downtimes Lists excessive downtime events for an org unit
Org units caddis_get_tree Returns the full organizational tree structure
Alarms caddis_list_alarms Lists active and historical alarms
Tags caddis_list_tags Lists all tags in your account
Tags caddis_get_tag Returns details for a specific tag
Tags caddis_list_tag_groups Lists all tag groups
Tags caddis_get_tag_group Returns details for a specific tag group
Runs caddis_list_runs Lists production runs for a machine or org unit
Runs caddis_get_run Returns details for a specific production run
Runs caddis_get_run_cycles Returns cycle data for a specific production run
Status caddis_list_status_reasons Lists all configured status reason codes for your account

Troubleshooting

Nothing happens after I add the server. Make sure you fully restarted your AI tool — most won't detect a new connection until relaunched.

No sign-in window appeared. Confirm your tool supports remote/HTTP MCP servers (not just local ones). Older tool versions, or tools without MCP/connector support yet, may not work.

I'm still using the old setup with a username and password. That version is retired. Remove it from your config and follow Step 1 above with the new URL.

Still stuck? Visit our support docs or contact the Caddis team.