IndustriConnect: MCP Adapters and Mock-First Evaluation for AI-Assisted Industrial Operations

Abstract

AI assistants can decompose multi-step workflows, but they do not natively speak industrial protocols such as Modbus, MQTT/Sparkplug B, or OPC UA, so this paper presents INDUSTRICONNECT, a prototype suite of Model Context Protocol (MCP) adapters that expose industrial operations as schema-discoverable AI tools while preserving protocol-specific connectivity and safety controls; the system uses a common response envelope and a mock-first workflow so adapter behavior can be exercised locally before connecting to plant equipment, and a deterministic benchmark covering normal, fault-injected, stress, and recovery scenarios evaluates the flagship adapters, comprising 870 runs (480 normal, 210 fault-injected, 120 stress, 60 recovery trials) and 2820 tool calls across 7 fault scenarios and 12 stress scenarios, where the normal suite achieved full success, the fault suite confirmed structured error handling with adapter-level uint16 range validation, the stress suite identified concurrency boundaries, and same-session recovery after endpoint restart is demonstrated for all three protocols, with results providing evidence spanning adapter correctness, concurrency behavior, and structured error handling for AI-assisted industrial operations.

Figures (7)

• Figure 1: IndustriConnect adapter architecture. An AI assistant issues MCP tool calls through a common JSON-RPC interface. The adapter layer handles protocol translation and safety guards, returning a shared response envelope. Each protocol adapter targets either a local mock (dashed) or real plant equipment.
• Figure 2: Repository protocol landscape with the three evaluated flagship adapters highlighted. This figure is supporting context, not evaluation evidence.
• Figure 3: MCP Manager UI used to register adapters and issue operator-style prompts. This figure is supporting context, not benchmark evidence.
• Figure 4: Per-task latency distributions across 30 repetitions. Box plots show median, interquartile range, and outliers.
• Figure 5: Error class distribution across the seven fault-injected tasks (30 runs each). Each color represents a distinct error category returned by the adapter.