With this method you can determine which alarms are currently active on the CPU, and when the last change occurred within the diagnostics buffer. To call the Alarms.Browse method, you need the
AI agents call Alarms-Browse to retrieve information from ThinkPLC-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the state of alarms and diagnostic information from a PLC controller. It retrieves data without creating, modifying, deleting, or executing operations. The blast radius of misuse is minimal — an attacker gains visibility into alarm status but cannot change system behavior or cause damage through this tool alone.
From the tool's definition Tool name 'Alarms-Browse' and description states 'determine which alarms are currently active' and 'when the last change occurred' — pure data retrieval with no modification or side effects.
Documented attack patterns abuse exactly the kind of access Alarms-Browse 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 Alarms-Browse:
{
"version": "1",
"default": "deny",
"tools": {
"Alarms-Browse": {}
}
} Alarms-Browse is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
With this method you can determine which alarms are currently active on the CPU, and when the last change occurred within the diagnostics buffer. To call the Alarms.Browse method, you need the. It is categorised as a Read tool in the ThinkPLC-MCP MCP Server, which means it retrieves data without modifying state.
Register the ThinkPLC- MCP server in PolicyLayer and add a rule for Alarms-Browse: 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.
Alarms-Browse 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 Alarms-Browse 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 Alarms-Browse. 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.
Alarms-Browse 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.