With the Plc.RequestChangeOperatingMode method, you request a new operating mode forthe CPU. Note that this is only a request for an operating mode. The conditions for an operating mode change must be given at the CPU, e.g. by the corresponding position of the mode selector. You can use the Plc.R...
AI agents invoke Plc-RequestChangeOperatingMode to trigger actions in ThinkPLC-MCP. 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.
Changing the operating mode of an industrial PLC is an Execute-category action with critical severity. Requesting a STOP mode on a live PLC could halt industrial processes, machinery, or safety systems, causing physical harm, equipment damage, or production outages. While it is described as a 'request' (not guaranteed), the blast radius of misuse is extremely high in an industrial control system context.
From the tool's definition 'request a new operating mode for the CPU' - this triggers an external operation on a physical PLC controller (SIEMENS S7-1500/1200), potentially switching between RUN/STOP/HALT modes
Documented attack patterns abuse exactly the kind of access Plc-RequestChangeOperatingMode gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ThinkPLC-MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for Plc-RequestChangeOperatingMode:
{
"version": "1",
"default": "deny",
"tools": {
"Plc-RequestChangeOperatingMode": {
"limits": [
{
"counter": "plc-requestchangeoperatingmode_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}Plc-RequestChangeOperatingMode stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
With the Plc.RequestChangeOperatingMode method, you request a new operating mode forthe CPU. Note that this is only a request for an operating mode. The conditions for an operating mode change must be given at the CPU, e.g. by the corresponding position of the mode selector. You can use the Plc.ReadOperatingMode method to check whether the operating mode change on the CPU was successful. To call the Plc.RequestChangeOperatingMode method, you need the. It is categorised as a Execute tool in the ThinkPLC-MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ThinkPLC- MCP server in PolicyLayer and add a rule for Plc-RequestChangeOperatingMode: 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 ThinkPLC-MCP. Nothing to install.
Plc-RequestChangeOperatingMode 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 Plc-RequestChangeOperatingMode 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 Plc-RequestChangeOperatingMode. 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.
Plc-RequestChangeOperatingMode is provided by the ThinkPLC- MCP server (mrwan84/thinkplc-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ThinkPLC-MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
23 ThinkPLC-MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.