AI agents call firewalla_search_flows 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 network flow data for inspection and monitoring without modifying any system state. It is explicitly part of a read-only server designed for auditing network activity. This is a classic Read operation—no side effects, no data modification, purely informational access.
From the tool's definition Tool name 'firewalla_search_flows' and server description stating 'read-only MCP server' and 'inspect' and 'without making any changes'. The tool searches/inspects network flows for auditing purposes.
Attacks that exploit this kind of access
Search network flows observed by Firewalla with the MSP query grammar. Use this to inspect what. 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_flows: 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_flows 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_flows 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_flows. 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_flows 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 →