Invoke a named Service on a Thing. Gated by THINGWORX_ALLOW_INVOKE=true (separate from write) because services execute named actions that can include PLC commands, scripted workflows, and downstream system calls. The MCP refuses to invoke unless the operator has explicitly authorized it.
AI agents invoke invoke_service to trigger actions in Thingworx. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
invoke_service runs code and external operations (PLC commands, scripted workflows, downstream calls) on an industrial control platform (ThingWorx IIoT). While gated by an environment variable, it remains Execute-category because the authorization gate does not change what the tool fundamentally does—trigger arbitrary named actions.
From the tool's definition Tool description states it 'Invoke[s] a named Service on a Thing' and 'services execute named actions that can include PLC commands, scripted workflows, and downstream system calls.' The explicit mention of executing PLC commands and downstream system calls…
Attacks that exploit this kind of access
Invoke a named Service on a Thing. Gated by THINGWORX_ALLOW_INVOKE=true (separate from write) because services execute named actions that can include PLC commands, scripted workflows, and downstream system calls. The MCP refuses to invoke unless the operator has explicitly authorized it. It is categorised as a Execute tool in the Thingworx MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Thingworx MCP server in PolicyLayer and add a rule for invoke_service: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Thingworx. Nothing to install.
invoke_service is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the invoke_service rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for invoke_service. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
invoke_service is provided by the Thingworx MCP server (nobanks/thingworx-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →