fortigate_explain_flow
AI agents call fortigate_explain_flow to retrieve information from Fortigate MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears designed to explain or analyze network flow data from a Fortigate firewall in a read-only diagnostic context. The empty description is a minor confidence reduction, but the consistent pattern of read-only sibling tools and explicit 'read-only' server description strongly indicate this retrieves/queries flow information without side effects.
From the tool's definition Tool name 'fortigate_explain_flow' combined with server description stating 'read-only querying and diagnostics' and 'traffic monitoring'. All sibling tools are read-only inspection/analysis functions (get_*, find_*, compare_snapshots, export_snapshot).
Attacks that exploit this kind of access
fortigate_explain_flow. It is categorised as a Read tool in the Fortigate MCP MCP Server, which means it retrieves data without modifying state.
Register the Fortigate MCP server in PolicyLayer and add a rule for fortigate_explain_flow: 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 Fortigate MCP. Nothing to install.
fortigate_explain_flow 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 fortigate_explain_flow 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 fortigate_explain_flow. 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.
fortigate_explain_flow is provided by the Fortigate MCP server (picaresco/mcp-fortigate). 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 →