report_incident · PolicyGuard MCP: Risk & Policy

WHAT IT DOES

What report_incident does on PolicyGuard

AI agents use report_incident to create or update resources in PolicyGuard — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your PolicyGuard environment.

WHY IT NEEDS A POLICY

Why report_incident needs a policy

Based on the tool name and server context (incident tracking, audit trails), 'report_incident' most likely creates or logs a new incident record in the system — a Write operation. The server description mentions 'incident tracking' as a core feature. Without a description, confidence is reduced, but reporting an incident is typically a reversible write action (creating a record).

From the tool's definition Tool name 'report_incident'; description is empty and uninformative.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

report_incident Rate-limited

report_incident stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "report_incident": {
      "limits": [
        {
          "counter": "report_incident_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about report_incident

What does the report_incident tool do? +

report_incident. It is categorised as a Write tool in the PolicyGuard MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on report_incident? +

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

What risk level is report_incident? +

report_incident is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit report_incident? +

Yes. Add a rate_limit block to the report_incident 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 report_incident completely? +

Set action: deny in the PolicyLayer policy for report_incident. 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 report_incident? +

report_incident is provided by the PolicyGuard MCP server (prateekkumar1709/policyguard). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.