System alarms within a date range.
AI agents call get_alarms to retrieve information from Enphase Solar 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 alarm information without any capability to modify, delete, or execute actions. It is a straightforward data query operation that returns historical alarm events. The blast radius of misuse is minimal—an unauthorized user could view alarm history but cannot trigger actions or affect system state. This falls squarely in the Read category with low severity.
From the tool's definition Tool name is 'get_alarms' which retrieves system alarms within a date range. The server description states 'read-only access' to solar production, consumption, battery, and EV charger data. This tool queries and returns alarm data without modification.
Attacks that exploit this kind of access
System alarms within a date range. It is categorised as a Read tool in the Enphase Solar MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Enphase Solar MCP Server MCP server in PolicyLayer and add a rule for 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 Enphase Solar MCP Server. Nothing to install.
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 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 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.
get_alarms is provided by the Enphase Solar MCP Server MCP server (xianman/enphase-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 →