// SCAN REPORT

Wtf

5 tools. 5 can modify or destroy data without limits.

5 write tools that can modify data. Rate limits recommended.

Last updated: 2 Jul 2026

5 can modify or destroy data

0 read-only

5 tools total

Community server · catalogue entry verified 02/07/2026

How to control Wtf ↓

TOOL MAP

What Wtf exposes to your agents

Read (0) Write / Execute (5) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Wtf tools

Write · Medium classify_entry The tool writes a classification back to the SQLite database for a given log entry. Write · Medium wtf_freshell The tool archives the current incident and initializes a new journal session. Write · Low wtf_imout The tool modifies session state by suspending the active troubleshooting session (stopping recording), but explicitly preserves captured data — no data is deleted or overwritten. Write · Low wtf_now The tool writes/records a journal entry into the SQLite flight recorder database.

5 of Wtf's 5 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Wtf

PolicyLayer is an MCP gateway — it sits between your AI agents and Wtf, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "classify_entry": {
    "limits": [
      {
        "counter": "classify_entry_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Create a free account and register Wtf — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON WTF →

Instant setup, no code required.

FULL CATALOGUE

All 5 Wtf tools

WRITE 5 tools

Write classify_entry Classify a troubleshooting log entry. Write wtf_freshell Archive the current incident and start a fresh journal. Previous entries are preserved in the database. Write wtf_happened Get a distilled timeline of the current troubleshooting incident. Writes a full runbook to .wtf/runbook.md. Write wtf_imout Suspend the active troubleshooting session. Stops recording but preserves captured data for later triage. Write wtf_now Record a journal entry in the WTF flight recorder. Use gen_type

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Wtf

How do I prevent bulk modifications through Wtf? +

The Wtf server has 5 write tools including classify_entry, wtf_freshell, wtf_happened. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Wtf.

How many tools does the Wtf MCP server expose? +

5 tools across 2 categories: Execute, Read. 0 are read-only. 5 can modify, create, or delete data.

How do I enforce a policy on Wtf? +

Register the Wtf MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Wtf tool call.

Deterministic rules across all 5 Wtf tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON WTF →

Instant setup, no code required.

5 Wtf tools catalogued and risk-classified — across an index of 43,000+ MCP servers.