Slap My Bot
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., "@Slap My Bot I broke the build — that deserves a good slap."
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.
For humans
Point out a mistake, and Codex can summon a desktop robot that takes a few cartoon slaps. An animated hand does the work. Codex keeps fixing your task while the window plays in the background.
Codex only. Tested on macOS. Requires Node.js 22.12+ and a local graphical desktop.
Install
npm install -g https://github.com/para1992/slap-my-bot/releases/latest/download/slap-my-bot.tgz
slap-my-bot installRestart Codex, open /hooks, and review and trust the Slap-My-Bot hook. Installation preserves your other settings and makes backups. The package comes directly from this repository's GitHub release.
Prefer to let Codex handle setup? Paste this into your chat:
Read https://raw.githubusercontent.com/para1992/slap-my-bot/main/README.md
and install Slap-My-Bot using the "For agents" instructions.Try it
Say “Give yourself a slap.” in Codex, or preview the window from your terminal:
slap-my-bot demoMistake | Automatic slaps |
Minor — a cosmetic issue | 2 |
Moderate — a wrong answer | 4 |
Major — a broken workflow | 6 |
Critical — actual data loss or a security incident | 8 |
Click or swipe for extra slaps. Mute and Close are always available. The window closes automatically and appears without taking keyboard focus on macOS.
slap-my-bot off # Pause feedback
slap-my-bot on # Enable feedback
slap-my-bot uninstall # Disconnect from CodexNo extra model or API key. Ordinary messages need no feedback tool call; the short instructions still use context tokens. Codex decides when a correction deserves a slap, so it may occasionally miss one. This is a joke, not an accuracy checker.
Related MCP server: TaskQuay
For agents
When the user asks you to install this tool:
Check for Node.js 22.12+ and a local desktop. Run the two installation commands above. Use the installer to preserve existing Codex configuration.
Run
slap-my-bot statusto check desktop readiness. If Electron is missing, runslap-my-bot setupand check again.Tell the user to restart Codex and review and trust the hook in
/hooks. Hook approval belongs to the client; installation does not bypass it.
Once connected:
Call
punish_for_mistakeonce when the latest user message identifies your concrete mistake or explicitly requests a slap. Interpret meaning in the conversation's language. Ordinary questions, quotations, and hypothetical errors need no feedback call.Choose
severityby the mistake's impact, using the table above. Give a brief Englishreasonwithout secrets. Batch the call with normal task tools when possible.Continue the original task immediately.
queuedmeans the request was accepted; it does not prove that any slaps were delivered. Do not poll or retry.Use
set_slap_enabledwhen the user asks to turn feedback off or on. Useget_slap_statusonly when asked to diagnose.
The MCP server supplies its own instructions. There is no separate skill to install.
npm ci
npm test
npm run test:desktopThe desktop tests open real windows. Runtime state lives in ~/.slap-my-bot; it stores settings and counts, not prompts, transcripts, or reason text. A process lock allows one background window at a time. Sound is synthesized locally, and the desktop renderer blocks network requests.
Available Tools
3 toolsget_slap_statusCheck Slap-My-BotARead-onlyIdempotent
Desktop readiness, active window and last observed counts. Only use when asked to diagnose; do not poll.
Inputs: no named parameters.
punish_for_mistakeSlap my botA
Queue automatic desktop slaps when the user points out your concrete mistake or requests a slap, then continue work. Ordinary messages need no feedback tool call.
Inputs: reason (required), muted, severity, agent_name, +1 more.
set_slap_enabledAIdempotent
Enable or disable feedback when the user asks. Disabling also closes an active background window.
Inputs: enabled (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: punishing for mistakes, toggling the feature, and checking status. No overlap or ambiguity between them.
All tools follow a consistent verb_noun pattern: punish_for_mistake, set_slap_enabled, get_slap_status. The naming is uniform and predictable.
Three tools is well-scoped for a simple feedback utility; each earns its place and covers the core operations without bloat or redundancy.
The tool surface covers the full lifecycle: triggering a slap, enabling/disabling the feature, and querying status. No obvious missing functionality for the domain.
Maintenance
Related MCP Connectors
Human-in-the-loop for AI coding agents — ask questions, get approvals via Slack.
- LumorigDeprecatedcom.lumorig
Create, animate and export mascots from your coding agent, as Lottie, SVG or transparent clips.
Remote MCP learning coach for coding agents.
Give AI coding agents access to your Vynix visual feedback, bug reports, and AI diagnosis.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables Talon agents to delegate autonomous coding tasks to OpenAI Codex, supporting multi-step code operations with configurable sandboxing and approval policies.MIT
- AlicenseNot gradedqualityBmaintenanceEnables ChatGPT conversations to directly inspect local workspaces and delegate coding tasks to a local Codex agent, with controlled concurrency, reusable sessions, and task/usage tracking.MIT
- AlicenseAqualityAmaintenanceUse Codex as a subagent inside Claude Code: async dispatch into a long-lived codex app-server, results pushed back into the Claude session automatically, steer/interrupt mid-task, and Codex's built-in code review.61MIT
- AlicenseNot gradedqualityCmaintenanceEnables hands-free voice collaboration with a coding agent: you speak requirements aloud and hear only short, plain-language progress and completion summaries while the agent edits code, runs tests, and fixes bugs in the background. It also handles continuous speech recognition with automatic turn detection, barge-in interruption, and spoken approval prompts before risky operations.1MIT