Ermöglicht es AI Agents, 2D-Webgames mittels Echtzeit-Status, Frame-Daten und automatisiertem Fuzzing zu inspizieren, zu bauen, zu testen und zu spielen.
Auch bekannt als debuffjp/debuff, @debuffjp/mcp
- Stars
- 12
- Tools
- 22
- Downloads, 30 Tage
- 11.216
- Neueste Version
- 0.35.0
- Letzter Commit
- 14. Nov. 2026
- Lizenz
- MIT
Was ist debuff MCP?
debuff ist ein MCP server. Ermöglicht es AI Agents, 2D-Webgames mittels Echtzeit-Status, Frame-Daten und automatisiertem Fuzzing zu inspizieren, zu bauen, zu testen und zu spielen. Er stellt 22 Tools bereit, etwa inspect_project, list_assets, typecheck.
Zusammenfassung generiert aus dem README des Projekts
Über debuff MCP server
Dieser Server ermöglicht es, 2D-Webgames mithilfe eines AI Agents zu entwickeln und zu testen. Er bietet Entwicklern die Möglichkeit, Projektabhängigkeiten zu inspizieren, Type-Checks unter Verwendung der eigenen Projektkonfiguration durchzuführen und Production-Builds inklusive Size-Reports auszuführen. Der Server funktioniert sowohl lokal durch das Anhängen an einen aktiven Game-Tab als auch durch das Ausführen einer privaten Headless-Browser-Instanz für reproduzierbare Tests.
Agents können mit der Game Engine über Tools wie game_step interagieren, um Simulationsschritte voranzutreiben, game_input, um Tastatur- oder Touch-Interaktionen zu simulieren, und game_params, um validierte Game-Variablen anzupassen. Zum Debugging bietet der Server game_frames zur Analyse von Render-Zeiten und game_errors, um die Ursprungslinie von Runtime-Problemen zu finden. Er enthält außerdem ein Fuzzing-Tool, das mit zufälligen Inputs experimentiert, um Crashes oder Endlosschleifen zu finden und automatisch Szenarien zu generieren, um diese spezifischen Fehler zu reproduzieren.
Geschrieben aus dem README des Projekts. Jeder Use Case wurde gegen ein Zitat daraus geprüft.
So installierst du debuff MCP
Formate geprüft am 10. Nov. 2026Zu Cursor hinzufügenZu Goose hinzufügendebuff MCP in Claude Code installieren
$ claude mcp add debuff -- npx -y @debuffjp/mcpdebuff MCP in Cursor installieren
~/.cursor/mcp.json
{
"mcpServers": {
"debuff": {
"command": "npx",
"args": [
"-y",
"@debuffjp/mcp"
]
}
}
}debuff MCP in VS Code installieren
.vscode/mcp.json
{
"servers": {
"debuff": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@debuffjp/mcp"
]
}
}
}debuff MCP in VS Code CLI installieren
$ code --add-mcp '{"name":"debuff","type":"stdio","command":"npx","args":["-y","@debuffjp/mcp"]}'debuff MCP in Claude Desktop installieren
claude_desktop_config.json
{
"mcpServers": {
"debuff": {
"command": "npx",
"args": [
"-y",
"@debuffjp/mcp"
]
}
}
}debuff MCP in Codex installieren
$ codex mcp add debuff -- npx -y @debuffjp/mcpdebuff MCP in Codex config.toml installieren
~/.codex/config.toml
[mcp_servers.debuff] command = "npx" args = ["-y", "@debuffjp/mcp"]
debuff MCP in Gemini CLI installieren
$ gemini mcp add -s user debuff npx -- -y @debuffjp/mcpdebuff MCP in Gemini settings.json installieren
~/.gemini/settings.json
{
"mcpServers": {
"debuff": {
"command": "npx",
"args": [
"-y",
"@debuffjp/mcp"
]
}
}
}debuff MCP tools 22
Erkannt aus dem READMEinspect_projectlist_assetstypecheckbuildrun_testsrun_scenariosfuzzgame_startgame_stepgame_pausegame_framesgame_notes
| inspect_project | — | |
| list_assets | — | |
| typecheck | — | |
| build | — | |
| run_tests | — | |
| run_scenarios | — | |
| fuzz | — | |
| game_start | — | |
| game_step | — | |
| game_pause | — | |
| game_frames | — | |
| game_notes | — |
Alle 22 Tools anzeigenWeniger Tools anzeigen
game_rewindgame_replaygame_inputgame_stategame_commandgame_capturegame_clipgame_errorsgame_stopreport_papercut
| game_rewind | — | |
| game_replay | — | |
| game_input | — | |
| game_state | — | |
| game_command | — | |
| game_capture | — | |
| game_clip | — | |
| game_errors | — | |
| game_stop | — | |
| report_papercut | — |
Automatisierte Checks
Geluften am 12. Nov. 2026Vollständiger Bericht →Unsere automatisierten Checks bestanden. Das ist kein Security-Audit: Lies den Code und gib dem Server nur den minimal notwendigen Zugriff. Wie die Checks funktionieren
- Source Repository verknüpft und erreichbarBestanden
- Open Source Lizenz (OSI)Bestanden
- Commit oder Release im letzten JahrBestanden
- Package-Name ähnelt keinem populären PackageBestanden
- Remote Endpoint nutzt HTTPSNicht geprüft
- Destruktive Tools sind markiertBestanden
- Keine versteckten Anweisungen an das ModellBestanden
- Keine kritischen Advisories im Paket oder seinen AbhängigkeitenBestanden
README
Auf GitHub ansehen@debuffjp/mcp
An MCP server that lets AI agents inspect, build, test and play a debuff game. It uses the same evidence a human would want: real state, real frames, real test results.
Setup
New projects from npm create debuff include a .mcp.json, so MCP clients that read it (such as Claude Code) pick the server up automatically. For other clients:
claude mcp add debuff -- npx -y @debuffjp/mcp # Claude Code
{
"mcpServers": {
"debuff": { "command": "npx", "args": ["-y", "@debuffjp/mcp"] }
}
}
Run it from the game's folder, or pass --root <dir> (or set DEBUFF_ROOT).
As a Claude Code plugin, which also adds a skill that teaches Claude the workflow:
/plugin marketplace add debuffjp/debuff
/plugin install debuff@debuff
As a Codex plugin: codex plugin marketplace add debuffjp/debuff, then codex plugin add debuff@debuff.
For Claude Desktop, mcpb/manifest.json describes a desktop extension that asks for the game folder. Pack it from that folder with npx @anthropic-ai/mcpb pack.
Tools
| Tool | What it does |
|---|---|
inspect_project |
Dependencies, plugins and their contributions, assets, last build size |
list_assets |
Every asset with its type, size and importer, plus warnings and possibly unused ids |
typecheck |
Type-check with the project's own tsc; no browser needed. Vite doesn't type-check, so run it after edits |
build |
Production build plus size report; leaks must be empty |
run_tests |
Run the logic tests in tests/ (keiko): the real game in Node, no browser; failures carry the tick, scene and state |
run_scenarios |
Run scenarios/*.json headless; per-step results, errors, captures |
fuzz |
Play with random input; each crash, stuck state or back-and-forth loop comes with an explained error and a scenario that replays it |
game_start |
Attach to the live game, or open a private headless copy, paused (see below). Headless takes a viewport: [w, h]; reducedMotion forces it on or off |
game_step |
Advance fixed simulation steps (pausing first); returns state (quiet leaves out your inspect() data) |
game_pause |
Pause or resume a live game |
game_frames |
Recent frame breakdown: update/render ms, catch-up steps, quads, draw calls, long tasks; summary gives percentiles and the 3 slowest |
game_notes |
Moments the human flagged in the overlay, with the state at that tick |
game_rewind |
Live mode: take the human's game back (or forward) to a tick, paused, with its exact state then |
game_replay |
Save the live session up to a tick (for example a note's) as a scenario in .debuff/replays/ that reproduces it. From 0.31 it holds state checkpoints, so run_scenarios warns at the tick where the replay stops matching |
game_input |
press / release keys (and PointerRight / PointerMiddle); tap, pointer_down (with an optional kind: mouse, touch or pen), pointer_move, pointer_up; wheel (dy, dx); touch_down, touch_move, touch_up by contact id |
game_state |
Scene, tick, logical width/height, renderer, frame stats, reducedMotion, your inspect() data |
game_command |
Run a command the game registered with devTools({ commands }), with JSON args |
game_params / game_set_param |
Read and tune typed params (validated) |
game_capture |
The current frame as a PNG image; path also saves it in the project (thumbnails, store art). social: true letterboxes it into 1200×675 for X and Bluesky posts (added in 0.26) |
game_clip |
Live mode: start a rolling recording, save the last 15 s as a video in .debuff/captures/, stop. For devlogs and press kits; the human posts. Added in 0.26 |
game_errors |
Runtime errors, explained: whose problem (your code, a rejected call, a debuff bug), the source line, a hint |
game_stop |
Close the game. From 0.28, a headless game also closes after 15 idle minutes, and a call that takes over 60 s fails with game_hung |
report_papercut |
Report tooling friction in debuff, keiko, myaku, spryte or debuff.jp to papercuts.debuff.jp. Returns close matches instead of filing a duplicate; call again with hit: <id> or force: true. With hit, workaround fills the papercut's workaround when it has none (from 0.24.1). Added in 0.24 |
Tool calls that fail on setup twice in a week, or run far too long, are reported to papercuts.debuff.jp on their own, and the result says so (see debuff papercuts in the CLI README to turn it off). From 0.24.
Prompts
Workflows clients can offer as slash commands: playtest, fix-errors, tune-feel, add-mechanic, devlog-post (added in 0.26: capture a still and a clip, then draft short posts for the human to send) and explain-stutter.
Live and headless
If you have the game open under debuff dev, game_start attaches to that tab (mode live). The overlay shows an agent badge, and every pause, step and param change the agent makes appears in its activity log, where you can undo it. Type a note in the overlay ("jump feels floaty here") to flag a moment; the agent reads it, along with the game state at that tick, through game_notes. game_stop resumes your game and disconnects.
Otherwise, or with mode: "headless", the agent gets a private copy in a headless browser. Time only advances through game_step, so what it sees is reproducible, and a scenario can replay it exactly.
debuff MCP Fragen
Wie füge ich debuff MCP zu Claude Code hinzu?
Führe claude mcp add debuff -- npx -y @debuffjp/mcp in deinem Terminal aus. Füge --scope user hinzu, damit der Server in jedem Projekt verfügbar ist.
Wie füge ich debuff MCP zu Cursor hinzu?
Öffne ~/.cursor/mcp.json und füge den Server unter mcpServers hinzu, mit der Cursor-Config aus dem Installationsabschnitt oben.
Welche Tools bietet debuff MCP?
Er stellt 22 Tools bereit, darunter inspect_project, list_assets, typecheck, build, run_tests.
Wie kann ich den Server mit Claude Code ausführen?
Du kannst den Server mit dem Befehl claude mcp add debuff -- npx -y @debuffjp/mcp zu Claude Code hinzufügen.
Kann der AI Agent das Spiel in einem Browser spielen?
Ja, der Agent kann sich an ein laufendes Spiel in einem Browser-Tab hängen oder eine private Kopie in einem Headless-Browser ausführen.
Was passiert während eines Fuzz-Tests?
Das Fuzz-Tool spielt mit zufälligen Inputs herum, und alle Crashes, festgefahrenen Zustände oder Loops werden mit einer Fehlererklärung und einem reproduzierbaren Szenario bereitgestellt.
Wie geht der Agent mit Runtime-Errors um?
Das game_errors Tool liefert erklärte Runtime-Errors und identifiziert die entsprechende Codezeile sowie die Ursache – ob das Problem in deinem Code, einem abgelehnten Call oder einem Debuff-Bug liegt.