phishfort_request_incident_action

WHAT IT DOES

What phishfort_request_incident_action does on Phishfort

AI agents invoke phishfort_request_incident_action to trigger actions in Phishfort. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why phishfort_request_incident_action needs a policy

This tool initiates external operational actions — particularly takedown requests — that affect external parties and infrastructure. While not directly destructive to data within the system, requesting a takedown triggers an irreversible external process targeting domains/content.

From the tool's definition 'Request takedown, monitoring, or safe review for an existing incident' — triggers external operations (takedown requests, monitoring activation) against third-party infrastructure via PhishFort's API

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

phishfort_request_incident_action Rate-limited

phishfort_request_incident_action stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "phishfort_request_incident_action": {
      "limits": [
        {
          "counter": "phishfort_request_incident_action_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Phishfort, so you can run agents against it safely.

FAQ

Questions about phishfort_request_incident_action

What does the phishfort_request_incident_action tool do? +

Request takedown, monitoring, or safe review for an existing incident. It is categorised as a Execute tool in the Phishfort MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on phishfort_request_incident_action? +

Register the Phishfort MCP server in PolicyLayer and add a rule for phishfort_request_incident_action: 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 Phishfort. Nothing to install.

What risk level is phishfort_request_incident_action? +

phishfort_request_incident_action is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit phishfort_request_incident_action? +

Yes. Add a rate_limit block to the phishfort_request_incident_action 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.

How do I block phishfort_request_incident_action completely? +

Set action: deny in the PolicyLayer policy for phishfort_request_incident_action. 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.

What MCP server provides phishfort_request_incident_action? +

phishfort_request_incident_action is provided by the Phishfort MCP server (mychaelconnolly/phishfort-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.