AI agents call read_property to retrieve information from Thingworx without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves live state data from industrial assets without creating, modifying, deleting, or executing side effects. It is a pure read operation on ThingWorx properties, presenting minimal risk unless the properties themselves contain sensitive credentials or control data—but the tool itself performs no destructive or state-changing actions.
From the tool's definition Tool name is 'read_property' and description states it 'Read[s] the current value of a single Property on a Thing' and 'Returns the property value plus its data type.' The phrase 'standard read path' confirms retrieval without modification.
Attacks that exploit this kind of access
Read the current value of a single Property on a Thing. Returns the property value plus its data type. The standard read path for an agent that needs the live state of an industrial asset. It is categorised as a Read tool in the Thingworx MCP Server, which means it retrieves data without modifying state.
Register the Thingworx MCP server in PolicyLayer and add a rule for read_property: 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.
read_property is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the read_property 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 read_property. 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.
read_property 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 →