Hobart Warewash MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOST | No | HTTP mode listen host. | 127.0.0.1 |
| PORT | No | HTTP mode listen port. | 3333 |
| HOBART_SCOPE | No | Override the production Hobart OAuth scope. Default is Machines.Read. | |
| HOBART_BASE_URL | No | Override the production Hobart API base URL. | |
| HOBART_PASSWORD | Yes | Your Hobart C2C account password. Required; can be provided as an environment variable or in ~/.config/hobart-warewash-mcp/.env. | |
| HOBART_USERNAME | Yes | Your Hobart C2C account username/email. Required; can be provided as an environment variable or in ~/.config/hobart-warewash-mcp/.env. | |
| MCP_HTTP_SECRET | No | Secret guarding the HTTP endpoint. Used in the connector URL path as /mcp/<MCP_HTTP_SECRET>, or as Authorization: Bearer <secret> for clients that can send headers. Without it, the HTTP server only answers on localhost. | |
| HOBART_CLIENT_ID | No | Override the production Hobart OAuth client ID. | |
| HOBART_ALLOW_WRITE | No | Set to true to expose the write tools. Read-only by default. | false |
| HOBART_TOKEN_ENDPOINT | No | Override the production Hobart OAuth token endpoint. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| hobart_pingA | Checks that the Hobart Cloud-to-Cloud API is reachable and that the configured account can sign in. Use it only when another tool fails and you need to know whether the problem is the connection. |
| hobart_list_machinesA | Lists the Hobart dishwashers registered on this account: serial number, machine type, protocol version and the machine clock at last contact. Start here: every other tool needs a serial number. |
| hobart_machine_overviewA | One-call health check of a dishwasher: active errors, last wash/rinse temperatures and the daily consumption figures. Prefer this to calling the three detail tools separately when the question is "how is machine X doing". |
| hobart_get_machine_dataA | Daily data of a dishwasher: consumption (DailyWaterCons, DailyEnergyCons, DailyDetergentCons, DailyRinseAidCons), counters (C0xx codes) and the hygiene protocol (one entry per wash cycle, with its program code). Hobart refreshes this only after the machine is powered off or shortly before midnight, so it describes the last completed day of use, not right now. |
| hobart_get_active_errorsA | Errors currently active on a dishwasher, with their code and since when. An empty list means no active error was reported, not that the machine is running. Hobart allows one real call every 30 seconds per machine; faster calls return the cached answer. |
| hobart_get_temperaturesA | Wash tank (A270) and rinse (A283) temperatures in °C, and the last program run. Hobart allows one real call every 60 seconds per machine; faster calls return the cached answer. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Tools target distinct resources, and the overview tool's overlap with get_machine_data/get_active_errors/get_temperatures is explicitly addressed in its description ('prefer this to calling the three detail tools separately'). The remaining ambiguity is between overview and get_machine_data, since both surface consumption figures; an agent must read the descriptions carefully to choose.
Most tools follow a hobart_verb_noun pattern (list_machines, get_machine_data, get_active_errors, get_temperatures), but machine_overview is noun-first and breaks the pattern, and ping is a bare verb with no object. Readable overall, but the convention is not uniform.
Six tools is well-scoped for a read-only machine-monitoring server, and each covers a real need (connectivity, enumeration, composite health, daily data, errors, temperatures). No padding or redundant endpoints beyond the deliberate overview convenience tool.
The surface covers the monitoring lifecycle well: discovery, connectivity, health summary, daily consumption/counters, active errors, and temperatures. Minor gaps exist around historical queries (no date-range or prior-day retrieval) and machine metadata (model/capabilities beyond type and protocol version), but agents can work around these.