AI agents call baseline_get_alarms to retrieve information from Baseline without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves alarm data from irrigation controllers without modifying, executing, or deleting anything. It is purely informational, reporting fault conditions that have already occurred. No side effects or state changes result from calling this tool. Low severity because misuse would only expose operational status information about irrigation systems, not cause direct harm to the system or data.
From the tool's definition Tool name includes 'get_' prefix and description states it retrieves 'Active alarms and faults' with decoding information.
Attacks that exploit this kind of access
Active alarms and faults for a controller (valve short circuits, flow comm failures, dial-off, empty conditions, etc.), decoded with sender device and fault type. It is categorised as a Read tool in the Baseline MCP Server, which means it retrieves data without modifying state.
Register the Baseline MCP server in PolicyLayer and add a rule for baseline_get_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 Baseline. Nothing to install.
baseline_get_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 baseline_get_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 baseline_get_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.
baseline_get_alarms is provided by the Baseline MCP server (swannman/baseline-irrigation-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 →