Query logged alarms from the storage system. The filterString parameter must be a valid ChromQueryLanguage (based on, and very similar to SQL) string, more specifically its WHERE part (without including the WHERE word itself). You can use most of the simple expressions in CQL, that are valid in S...
AI agents call get-logged-alarms to retrieve information from WinCC Unified MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical alarm data from storage using query filters. It is fundamentally a read operation that queries existing data without side effects like modification or deletion.
From the tool's definition Query logged alarms from the storage system. The tool accepts a filterString parameter to query historical alarm data with expressions similar to SQL WHERE clauses.
Documented attack patterns abuse exactly the kind of access get-logged-alarms gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and WinCC Unified MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get-logged-alarms:
{
"version": "1",
"default": "deny",
"tools": {
"get-logged-alarms": {}
}
}get-logged-alarms 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.
Query logged alarms from the storage system. The filterString parameter must be a valid ChromQueryLanguage (based on, and very similar to SQL) string, more specifically its WHERE part (without including the WHERE word itself). You can use most of the simple expressions in CQL, that are valid in SQL. The column names must be valid logged alarm attributes. You can use wildcards (* to match with any number of characters, ? to replace exactly one character), less-than and greater-than, equal and similar operators, and you can use parentheses to group the expressions and connect them with logical operators such as OR or AND. If the filterString contains any comparison with multilingual texts, the filterLanguage parameter is used to decide, which language of the texts should be compared. All multilingual texts will be returned in the languages specified in the languages parameter. All language identifying parameters must be provided in ISO language code format (e.g. It is categorised as a Read tool in the WinCC Unified MCP Server MCP Server, which means it retrieves data without modifying state.
Register the WinCC Unified MCP Server MCP server in PolicyLayer and add a rule for get-logged-alarms: 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 WinCC Unified MCP Server. Nothing to install.
get-logged-alarms 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 get-logged-alarms 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 get-logged-alarms. 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.
get-logged-alarms is provided by the WinCC Unified MCP Server MCP server (vogler75/winccua-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from WinCC Unified MCP Server, 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.
9 WinCC Unified MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.