AI agents call firewalla_search_alarms to retrieve information from Firewalla without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries alarm data from the Firewalla system. It has no side effects, cannot modify or delete data, and cannot execute commands. It is a pure read operation consistent with the server's read-only design. The low severity reflects minimal blast radius even if misused—worst case is excessive alarm queries or information disclosure of existing alarms.
From the tool's definition Tool description states 'Search active Firewalla alarms' and server is explicitly described as 'read-only MCP server' that 'provides tools to inspect devices, rules, alarms, and traffic flows without making any changes'.
Attacks that exploit this kind of access
Search active Firewalla alarms with the MSP query grammar. This is the primary tool for. It is categorised as a Read tool in the Firewalla MCP Server, which means it retrieves data without modifying state.
Register the Firewalla MCP server in PolicyLayer and add a rule for firewalla_search_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 Firewalla. Nothing to install.
firewalla_search_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 firewalla_search_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 firewalla_search_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.
firewalla_search_alarms is provided by the Firewalla MCP server (productengineered/firewalla-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 →