factory-supervisor-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 |
|---|---|
| tasks | {
"list": {},
"cancel": {},
"requests": {
"tools": {
"call": {}
}
}
} |
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"subscribe": true,
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| pingB | Diagnostic health check ping tool for Factory Supervisor MCP Server |
| getMachineStatusA | Get status details for a specific machine by machineId |
| listMachinesA | List all factory machines and their current state |
| getInventoryA | Get total inventory stock levels for all parts |
| getLowStockItemsA | Get inventory items where available stock is at or below reorder level |
| getOrdersB | Get factory production orders |
| getMaintenanceLogsA | Get factory maintenance logs and history |
| getProductionScheduleB | Get factory production schedule |
| getFactoryKPIsA | Get key performance indicators (KPIs) for the factory |
| analyzeFactoryB | Consolidates data across all factory modules (machines, inventory, orders, maintenance, schedule, KPIs) and generates severity levels, health score (0-100), natural language summary, risk classification, impact score, and recommendations. |
| predictMachineFailureA | Predicts failure probability, health score, estimated failure time window, and recommended actions for a machine based on sensor telemetry. |
| forecastInventoryB | Forecasts stockout date, days remaining, inventory risk level, and recommended reorder quantity for inventory parts. |
| estimateOrderCompletionB | Estimates completion time, confidence score, and delay risk for a given production order. |
| detectProductionBottlenecksA | Detects active and impending production bottlenecks across machines, inventory, and shifts. |
| predictFactoryHealthA | Predicts overall factory health score trends for today and tomorrow based on operational indicators. |
| factoryCopilotA | Natural language AI supervisor assistant that routes user questions to appropriate analytics and predictive MCP tools to generate actionable answers. |
| dailySupervisorBriefA | Generates a concise daily supervisor briefing highlighting overall factory health, top operational risks, and priority actions. |
| executiveSummaryA | Provides a high-level executive summary of factory performance, revenue exposure risk, and recommended strategic decisions. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Health Checks | Current health status of all registered health checks |
| Widget Examples | Provides metadata and examples for all registered UI widgets |
TDQS
Scored across 18 tools
Most tools have clearly distinct purposes: inventory, machines, orders, maintenance, schedule, KPIs. However, the five high-level analytics/summary tools (analyzeFactory, predictFactoryHealth, factoryCopilot, dailySupervisorBrief, executiveSummary) could be confused due to overlapping outputs like health scores and recommendations, though their descriptions partially clarify target audiences.
The naming pattern is largely consistent with verb-first camelCase (getInventory, listMachines, predictMachineFailure, etc.). Exceptions like factoryCopilot, dailySupervisorBrief, executiveSummary, and ping deviate from this pattern, but they remain readable and semantically descriptive.
Eighteen tools is slightly above the typical 3-15 well-scoped range, but each tool maps to a distinct aspect of factory supervision (status reads, predictions, forecasts, summaries). The count feels justified for the broad domain, though it is on the heavier side.
The tool set covers all major factory modules (machines, inventory, orders, maintenance, schedule, KPIs) with both operational reads and predictive analytics. Minor gaps include per-order detail retrieval or explicit shift/employee data, but these are not critical for the supervisor role.