wtf_happened · Wtf MCP: Risk & Policy

WHAT IT DOES

What wtf_happened does on Wtf

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

WHY IT NEEDS A POLICY

Why wtf_happened needs a policy

While the tool retrieves a distilled timeline (Read), it also writes a runbook file to disk (.wtf/runbook.md), which is a side-effecting Write operation. The most severe applicable category is Write. Severity is medium because it creates/overwrites a file in the working directory, which could overwrite existing runbook content, but the blast radius is limited to a local markdown file.

From the tool's definition 'Writes a full runbook to .wtf/runbook.md' indicates file creation/modification on disk

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

wtf_happened Rate-limited

wtf_happened 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": {
    "wtf_happened": {
      "limits": [
        {
          "counter": "wtf_happened_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 Wtf, so you can run agents against it safely.

FAQ

Questions about wtf_happened

What does the wtf_happened tool do? +

Get a distilled timeline of the current troubleshooting incident. Writes a full runbook to .wtf/runbook.md. It is categorised as a Write tool in the Wtf MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on wtf_happened? +

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

What risk level is wtf_happened? +

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

Can I rate-limit wtf_happened? +

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

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

wtf_happened is provided by the Wtf MCP server (wave-engineering/mcp-server-wtf). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.