mcp-server-wtf
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-server-wtfshow me the timeline of the current incident"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
WTF (Why That Failed)
A flight recorder for incident troubleshooting inside Claude Code. WTF captures every tool call and manual observation into a durable SQLite database that survives context compaction, then enriches raw entries through a background classifier into a distilled timeline.
Prerequisites
Claude Code CLI (
claude)jq(JSON processor)curlorwgetAWS credentials for Bedrock (optional — enables background classifier)
Related MCP server: Claude Code Toolkit
Installation
curl -fsSL https://raw.githubusercontent.com/Wave-Engineering/mcp-server-wtf/main/scripts/install-remote.sh | bashThis downloads a pre-compiled binary for your platform, installs the
PostToolUse hook, and registers the MCP server. No clone or runtime required.
Skills (/wtf, /wtf now, /wtf happened, /wtf imout) are delivered by
claudecode-workflow.
Verify the installation:
curl -fsSL https://raw.githubusercontent.com/Wave-Engineering/mcp-server-wtf/main/scripts/install-remote.sh | bash -s -- --checkInstall a specific version:
curl -fsSL https://raw.githubusercontent.com/Wave-Engineering/mcp-server-wtf/main/scripts/install-remote.sh | bash -s -- --version v1.0.0Development Installation
If you're working on the WTF server itself, clone the repo and use the local installer (requires Bun):
git clone https://github.com/Wave-Engineering/mcp-server-wtf.git
cd mcp-server-wtf
./scripts/install.shQuick Start
# Start troubleshooting
/wtf
# Investigate the issue... Claude records tool calls automatically
# Get the distilled timeline
wtf_happened
# Add your own observations
/wtf now "DNS resolver returning stale records"Architecture Overview
WTF is a three-layer system:
/wtf, /wtf now Skills (user-facing entry points)
|
v
wtf_now, wtf_happened MCP Server (journal storage, retrieval,
wtf_freshell background classification)
^
|
PostToolUse hook Auto-capture (every tool call -> JSONL queue)Layer 1 -- Skills: /wtf starts a troubleshooting session and activates
flight recorder mode. /wtf now adds manual journal entries.
Layer 2 -- MCP Server: A Bun + TypeScript server exposing four tools over stdio transport. Manages a SQLite database, ingests the hook queue, and runs a background classifier (Claude Haiku via AWS Bedrock) that categorizes entries as actions, breadcrumbs, theories, or noise.
Layer 3 -- PostToolUse Hook: A shell script that fires on every Claude Code
tool call, extracts relevant fields, truncates large values, and appends a JSON
line to .wtf/hook-queue.jsonl for ingestion.
Usage
Starting a Session
/wtfArchives any prior incident and creates a fresh one. Prompts for an optional title, then puts Claude into flight recorder mode where significant observations are journaled automatically.
Recording Observations
/wtf now the health endpoint is returning 503s
/wtf now "theory: connection pool exhaustion under load"
/wtf now checked nginx logs — 502s started at 14:32Adds a manual entry to the journal. Classification is handled by the background classifier.
Getting the Timeline
Call the wtf_happened MCP tool (Claude can invoke it directly, or you can ask
for it):
wtf_happened # summary (max 50 lines)
wtf_happened { detail: "full" } # all entriesReturns a distilled Markdown timeline:
## WTF Summary -- DNS Resolution Failure
**Duration:** 45 min | **Entries:** 127 raw, 34 distilled | **Status:** active
1. [12:03] BREADCRUMB -- Health endpoint returning 503s intermittently
2. [12:05] THEORY -- Connection pool exhaustion, idle timeout set to 0
3. [12:08] ACTION -- Set DB_POOL_IDLE_TIMEOUT=30s in .envSuspending Recording
/wtf imoutSuspends the flight recorder without losing data. Useful when switching to non-troubleshooting work. The hook still fires but entries are filtered.
Generating a Runbook
wtf_happened also writes a runbook skeleton to .wtf/runbook.md that can be
refined into a reusable playbook.
Clearing / Starting Fresh
wtf_freshellArchives the current incident and starts a new one. Previous entries are preserved in the database.
Configuration
Data Directory
All runtime data lives in .wtf/ relative to the project root (gitignored):
.wtf/
wtf.db SQLite database (WAL mode)
hook-queue.jsonl Hook queue (consumed by MCP server)
runbook.md Generated runbook skeletonTunable Values
Parameter | Default | Location |
Queue poll interval | 2,000 ms |
|
Classifier poll interval | 5,000 ms |
|
Classifier rate limit | 2,000 ms |
|
Hook truncation limit | 4,096 bytes |
|
Summary line cap | 50 lines |
|
MCP Server Registration
The remote installer registers the compiled binary:
claude mcp add --scope user --transport stdio wtf-server -- ~/.local/bin/wtf-serverThe development installer registers the Bun source directly:
claude mcp add --scope user --transport stdio wtf-server -- bun /path/to/mcp-server-wtf/index.tsHook Configuration
The PostToolUse hook is configured in ~/.claude/settings.json:
{
"hooks": {
"PostToolUse": [
{
"type": "command",
"command": "/absolute/path/to/scripts/hooks/wtf-post-tool-use.sh"
}
]
}
}Uninstall
If installed via the remote installer:
curl -fsSL https://raw.githubusercontent.com/Wave-Engineering/mcp-server-wtf/main/scripts/install-remote.sh | bash -s -- --uninstallIf installed from a local clone:
./scripts/install.sh --uninstallBoth remove the MCP server registration and hook configuration. The
per-project .wtf/ data directories are preserved (they contain incident
history). To remove them:
rm -rf .wtf/License
MIT -- see LICENSE.
This server cannot be deployed
Maintenance
Related MCP Connectors
Persistent, governed institutional memory for Claude Code — specs, decisions, learnings.
Persistent, outcome-grounded episodic memory for Claude. 14ms CPU retrieval, no GPU, no vector DB.
Source-checked CLI guides and model-aware planning for Claude Code, Codex, and Grok Build.
Codebase graphs, caller impact analysis, and recorded project context for AI coding agents.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceReal-time audit and approval system for Claude Code tool calls, enabling monitoring and control of AI agent actions with a web dashboard.19MIT
- AlicenseAqualityFmaintenanceMaintenance, recovery, and observability for Claude Code. CLI + MCP server + dashboard.4029 npm108MIT
- AlicenseNot gradedqualityDmaintenanceA multi-agent collaboration tool for Claude Code that supports hot-swappable role YAML, persistent memory with SQLite and FTS5, and step-level replay in a single-file HTML viewer.1MIT
- AlicenseNot gradedqualityDmaintenanceA lightweight journal/memory system for Claude Code with no ML dependencies, using SQLite for fast local storage.6MIT