Neural Cosmology
Answers, essays, experiments and books on consciousness and cosmology: search, read, buy.
Beschreibung vom Entwickler (englisches Original)
Zero-addon MCP server for Godot 4: agents edit, run, and play-test the game.
Diese drei werden nie zu einer Punktzahl zusammengefasst: Meinungen, Messungen und Beliebtheit sind verschiedene Dinge.
Für diesen Server haben wir noch keine Zusammenfassung in einfacher Sprache geschrieben. Unten stehen die Fakten, die wir aus der Registry gelesen haben.
Wähle die KI-App, die du nutzt, und kopiere die Einstellungen.
GODOT_PATH, DEBUG, GODOT_MCP_DISABLE_ELICITATION, GODOT_MCP_STRICT, GODOT_MCP_DISABLE_SECURITYDu brauchst
Welche App nutzt du?
Wähle oben deine App. Wir merken sie uns, damit der Button beim nächsten Mal „In … installieren“ anzeigt.
Öffne Claude Desktop → Settings → Developer → Edit Config und füge dies in claude_desktop_config.json ein
{
"mcpServers": {
"godot-runtime": {
"command": "npx",
"args": [
"-y",
"godot-mcp-runtime"
],
"env": {
"GODOT_PATH": "your-value",
"DEBUG": "your-value",
"GODOT_MCP_DISABLE_ELICITATION": "your-value",
"GODOT_MCP_STRICT": "your-value",
"GODOT_MCP_DISABLE_SECURITY": "your-value"
}
}
}
}Führe das in deinem Terminal aus
claude mcp add godot-runtime --env GODOT_PATH=your-value --env DEBUG=your-value --env GODOT_MCP_DISABLE_ELICITATION=your-value --env GODOT_MCP_STRICT=your-value --env GODOT_MCP_DISABLE_SECURITY=your-value -- npx -y godot-mcp-runtimeTrag die leeren Werte ein, bevor du ihn startest.
In .cursor/mcp.json in deinem Projekt oder in ~/.cursor/mcp.json einfügen
{
"mcpServers": {
"godot-runtime": {
"command": "npx",
"args": [
"-y",
"godot-mcp-runtime"
],
"env": {
"GODOT_PATH": "your-value",
"DEBUG": "your-value",
"GODOT_MCP_DISABLE_ELICITATION": "your-value",
"GODOT_MCP_STRICT": "your-value",
"GODOT_MCP_DISABLE_SECURITY": "your-value"
}
}
}
}Dein Browser fragt, ob er die App öffnen darf, dann zeigt die App die Einstellungen und bittet dich um Bestätigung. Schlüsselwerte bleiben leer, damit du sie selbst einträgst.
In .vscode/mcp.json in deinem Projekt einfügen
{
"servers": {
"godot-runtime": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"godot-mcp-runtime"
],
"env": {
"GODOT_PATH": "your-value",
"DEBUG": "your-value",
"GODOT_MCP_DISABLE_ELICITATION": "your-value",
"GODOT_MCP_STRICT": "your-value",
"GODOT_MCP_DISABLE_SECURITY": "your-value"
}
}
}
}Dein Browser fragt, ob er die App öffnen darf, dann zeigt die App die Einstellungen und bittet dich um Bestätigung. Schlüsselwerte bleiben leer, damit du sie selbst einträgst.
Dieser Server läuft auf deinem Computer, und ChatGPT kann sich nur mit Servern im Internet verbinden. Wähle eine andere App.
Deine Auswahl bleibt in einem Cookie auf diesem Gerät; kein Konto nötig.
GODOT_PATH envDEBUG envGODOT_MCP_DISABLE_ELICITATION envGODOT_MCP_STRICT envGODOT_MCP_DISABLE_SECURITY envDiese Einstellungen werden aus dem Registry-Eintrag des Entwicklers erzeugt. Wenn in der README etwas anderes steht, folge der README.
Läuft auf deinem Computer; die Tool-Liste erscheint nach der Installation in deiner KI-App.
Wir prüfen Informationen, die jeder sehen kann; den Code haben wir nicht gelesen. Checks, die nicht zutreffen, werden nicht mitgezählt. · Geprüft am 7. Nov. 2026
Der Registry-Name wurde mit dem GitHub-Konto Erodenn bestätigt, dem das Repo gehört
Dieses Repo haben wir noch nicht von GitHub gelesen
Dieses Repo haben wir noch nicht von GitHub gelesen
Dieser Server läuft auf deinem Computer; es gibt keinen Endpunkt im Internet
Läuft auf deinem Computer und nutzt stattdessen lokale Einstellungen
Läuft auf deinem Computer; Tool-Listen können wir nur von Endpunkten im Internet lesen
Verglichen mit allen aktiven Servern dieser Kategorie in der Registry. Sterne zählen nur, wenn dem Herausgeber das Repo gehört.
Er hat 1 von 1 zutreffenden Basischecks bestanden. Den Code haben wir nicht gelesen. Bevor du einen Schlüssel oder Token hinzufügst, sieh nach, welche Zugriffe der Server verlangt, und nutze einen Schlüssel, der nur die Berechtigungen hat, die du brauchst.
Die Registry nennt keinen erforderlichen Schlüssel, manche Server bitten dich aber bei der ersten Nutzung, dich anzumelden.
Er läuft auf deinem Computer. Deine KI-App startet ihn bei Bedarf, und die Daten laufen nicht über die Server des Entwicklers (außer der Server ruft selbst einen Onlinedienst auf).
Das GitHub-Repo wurde zuletzt – geändert, und die neueste Version (3.8.0) kam vor 2 Monaten in die Registry.
Apps, die MCP unterstützen, etwa Claude Desktop, Claude Code, Cursor und VS Code. Außerdem brauchst du Node.js auf deinem Computer.
In derselben Kategorie: Neural Cosmology, slopped.site, Artsonia MCP
Server derselben Kategorie von anderen Entwicklern, sortiert nach Sternen.
So liest du eine Karte:★ GitHub-SterneiDrei Säulen: Bewertungen · Checks · NutzungiAktualisiert = neueste Version in der Registry veröffentlichti
Answers, essays, experiments and books on consciousness and cosmology: search, read, buy.
Read-only tools over slopped.site: AI-made art, lore, games, sites, the curriculum.
Parent/fan access to Artsonia student-art portfolios, comments, and fans (AI-built).
Unverändert aus dem Repo des Entwicklers übernommen. PopNx MCP hat den Inhalt weder geprüft noch empfiehlt es ihn. HTML, Bilder und Skripte wurden entfernt. Links führen von dieser Website weg.
A lightweight MCP server that gives AI agents the tools to interact with the Godot game engine. Features comprehensive headless editing and full runtime control over a Godot 4.x project. Scene, node, autoload, and validation ops cover everything short of the most niche corners of the engine; the runtime bridge adds screenshots, input simulation, UI discovery, and live GDScript against the running scene tree.
The AI doesn't just write your game, it can check its work.
No addon required. Most Godot MCP servers that offer runtime support ship as a Godot addon, something you install into your project, commit to version control, and manage as a dependency. Use npx and there's no install or setup needed.
Think of it as Playwright MCP, but for Godot. This does the same thing for games: run the project, take a screenshot, simulate input, read what's on screen, execute a script against the live scene tree. The agent closes the loop on its own changes rather than handing off to you to verify.
[!NOTE]
This is not a playtesting replacement. It doesn't catch the subtle feel issues that only a human notices, and it won't tell you if your game is fun. What it does is let an agent confirm that a scene loads, a button responds, a value updated, a script ran without errors. The ability to check work is crucial for AI driven workflows.
This server is the perfect tool kit for AI assisted game development with Godot. It provides a comprehensive suite of tools that allows agents to create scenes, nodes, scripts, and more. The runtime tool set provides the capabilities to check work by running the game and interacting with it in real time, all without becoming a cumbersome dependency on your project.
Built for agents. Every tool is purpose-built and self-documenting. When something fails, the response tells the agent how to fix it; when something succeeds, it points toward the next step. The result is an AI that stays unstuck and self-corrects without needing you to nudge it along.
Headless editing. Create scenes, add nodes, set properties, attach scripts, connect signals, validate GDScript. All the standard operations, no editor window required.
Runtime bridge. When run_project or attach_project is called, the server injects McpBridge as an autoload. This opens a localhost-only TCP listener (both auto-select a free port when bridgePort is omitted; pass bridgePort to pin a specific port) and enables:
profiling: true at launch, capture Godot's own profiler and rank the most expensive GDScript functions by own or inclusive time, with source locations and per-frame averagesBackground mode. Pass background: true to run_project and the Godot window moves off-screen (positioned at (-9999, -9999)) with physical input blocked: borderless, unfocusable, mouse-passthrough. Programmatic input, screenshots, and all runtime tools work exactly the same. Useful for automated agent-driven testing where the window shouldn't be visible or interactive.
Manual attach mode. When something other than MCP launches the game (a CI pipeline, an external debugger, your own shell), call attach_project first. It injects the bridge and marks the project active without spawning Godot, so when you launch the game manually, runtime tools work against it. Use detach_project when done.
[!IMPORTANT]
get_debug_outputis unavailable in attached mode. stdout and stderr only flow through processes MCP started itself, so when Godot is launched externally there's no captured output to return. Userun_projectif you need the debug stream.
The bridge cleans itself up automatically - on stop_project or detach_project, and also without a tool call when the game exits on its own, the bridge connection drops, or the server shuts down (including a client that just closes the connection). Its artifacts live under .mcp/godot-runtime/ in the project, which the server adds to .gitignore. No leftover autoloads, no modified project files.
The Godot MCP space splits on two axes: whether a server can drive a _running_ game (runtime) or only edit files, and what it costs your project to do so. Most servers that offer real runtime control ship as a Godot addon you install and commit to version control, or as a custom engine you download. This one injects a bridge transiently and removes it on shutdown, so you get full live-game control against stock Godot with nothing left in your repo.
| Server | Live-game runtime | Footprint | License | Price |
|---|---|---|---|---|
| Godot MCP Runtime | Full: screenshots, input, live scene tree, script exec | Zero (npx, no committed addon) | MIT | Free |
| Summer Engine | Full | Custom engine download + sign-in | MIT layer / proprietary engine | Free core, paid cloud |
| tugcantopaloglu/godot-mcp | Full | Committed autoload addon | MIT | Free |
| Godot MCP Pro | Full | Committed editor addon | Proprietary | $15 |
| GDAI MCP | Editor-mediated | Committed editor addon | Proprietary | $19 |
| Coding-Solo/godot-mcp | No (launch + debug output) | Zero (npx) | MIT | Free |
Among servers with full live-game control, Godot MCP Runtime pairs a zero-footprint install (no addon committed to version control, no custom engine, no account) with a single npx command, and it has shipped this transient-autoload runtime bridge since February 2026. For the full field of ~20 servers with a source for every claim, see docs/comparison.md.
That's it. No Godot addon, no project modifications.
Add the following to your MCP client config. Works with Claude Code, Claude Desktop, Cursor, or any MCP-compatible client. Ask your AI assistant to call check_project. If it returns a Godot version string (e.g., 4.4.stable), you're connected and working.
Zero-install via npx (recommended):
{
"mcpServers": { "godot": { "command": "npx", "args": ["-y", "godot-mcp-runtime"], "env": { "GODOT_PATH": " " } } } }
Or install globally:
npm install -g godot-mcp-runtime
{
"mcpServers": { "godot": { "command": "godot-mcp-runtime", "env": { "GODOT_PATH": " " } } } }
Or clone from source:
git clone https://github.com/Erodenn/godot-mcp-runtime.git
cd godot-mcp-runtime npm install npm run build
{
"mcpServers": { "godot": { "command": "node", "args": [" /godot-mcp-runtime/dist/index.js"], "env": { "GODOT_PATH": " " } } } }
[!TIP]
Prefer pnpm? All three install paths work with pnpm. Substitute
pnpm dlx godot-mcp-runtimefornpx -y godot-mcp-runtime,pnpm add -g godot-mcp-runtimefor the global install, orpnpm install && pnpm run buildfor the source build. pnpm ships stronger defaults against npm supply-chain attacks; see pnpm's supply chain security guide.
If Godot is on your PATH, you can omit GODOT_PATH entirely. The server will auto-detect it.
All are set in the same env block as GODOT_PATH:
| Variable | Effect |
|---|---|
DEBUG | "true" enables verbose [DEBUG] logging. |
The three security-gate flags below share one axis (see docs/security.md for the full picture) and are wide enough to wrap badly in a table, so they get a list instead:
"true" disables the confirmation prompts for run_project and run_script. Use this if your client cannot display elicitation prompts (e.g. Claude Desktop, which auto-cancels them). Fail-open: the action proceeds with a warning. Tier 1 security hard-blocks still apply."true" hard-rejects anything that would otherwise prompt, for unattended operation. Takes precedence over GODOT_MCP_DISABLE_ELICITATION when both are set."true" turns the entire run_script/run_project security gate off: no scan, no block, no elicitation, no warnings, no audit sidecars - Tier 1 included. Overrides GODOT_MCP_STRICT when both are set. Enabling this is a human decision - an agent should decline to set it on a user's behalf.{
"mcpServers": { "godot": { "command": "npx", "args": ["-y", "godot-mcp-runtime"], "env": {
Nur der Anfang wird gezeigt; den Rest findest du im Repo