Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add XOVIET-GAME/godot-mcp --skill godot-interactivegit clone --depth 1 https://github.com/XOVIET-GAME/godot-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/xoviet-game/godot-mcp/godot-interactive)<a href="https://agentmods.dev/skills/xoviet-game/godot-mcp/godot-interactive"><img src="https://agentmods.dev/badge/skills/xoviet-game/godot-mcp/godot-interactive/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/xoviet-game/godot-mcp/godot-interactive"><img src="https://agentmods.dev/badge/skills/xoviet-game/godot-mcp/godot-interactive.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00033 | $0.01990 |
| Opus 5 | $0.00016 | $0.00995 |
| Sonnet 5 | $0.00007 | $0.00398 |
| Haiku 4.5 | $0.00003 | $0.00199 |
Grade A, and why
godot-interactive scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Godot Interactive Workflow
Use this skill for repeatable Godot project interaction: inspect the current files, make a bounded change, run the game, send input, collect state and diagnostics, and leave an evidence-backed result.
Current MCP surface
This repository exposes one catalog tool and eighteen grouped tools. The grouped tools are:
core_manage, project_manage, scene_manage, filesystem_manage, validation_manage, runtime_manage, node_manage, input_manage, signal_manage, animation_manage, camera_manage, physics_manage, render_2d_manage, render_3d_manage, audio_manage, ui_manage, network_manage, and system_manage.
Start with:
{ "domain": "runtime" }
passed to godot_catalog. The response lists the exact operation names and schemas for that domain. Then call the matching grouped tool:
{
"op": "game_wait",
"params": { "frames": 5, "frameType": "render" }
}
The outer object is passed to runtime_manage. Never promote an operation name into a standalone MCP tool name, and always include params as an object.
Transport and lifecycle
There is no editor-side AI Bridge in this repository and no editor connection API on TCP port 6550. The server launches the Godot project, copies/injects its interaction autoload, and connects to the runtime interaction server at 127.0.0.1:9090. Runtime commands only work after a project is running and the injected server has initialized.
Start a project with:
{
"op": "run_project",
"params": {
"projectPath": "C:/games/demo",
"scene": "res://scenes/main.tscn"
}
}
passed to core_manage. The scene parameter is optional. Stop it with { "op": "stop_project", "params": {} }. Use { "op": "get_debug_output", "params": {} } on core_manage for captured stdout/stderr. There is no separate connect, disconnect, editor refresh, or editor-save phase in this public tool tree.
Session loop
1. Establish a baseline
Inspect project metadata and persisted scene structure before changing anything:
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 234 lines · 33 tokens per session scan A e0994a4e38c4
godot-interactive is a skill published in the GitHub repository XOVIET-GAME/godot-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 1,990 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
minecraft-debug-mcp
Operate and debug the live Minecraft bot through its built-in MCP REPL server. Use when work requires starting the bot with pnpm dev, connecting to the local MCP endpoint, inspecting cognitive state/logs/history, injecting synthetic chat/events, or running targeted REPL code against the running brain during…
graphics-api-hooking
Analyze Direct3D/DXGI, OpenGL, and Vulkan rendering, presentation, composition, and capture evidence. Use to distinguish API samples, PresentMon event metrics, Tracy instrumentation, compatibility translation, frame images, and validation diagnostics; review swap chains, overlays, resource lifetime, and…
console-get-logs
Retrieve Unity Editor logs from the MCP plugin's LogCollector, optionally filtered by log type or time window. Useful for debugging and monitoring Editor activity.
editor-application-get-state
Return the current state of UnityEditor.EditorApplication — playmode, paused state, compilation state, and related flags.
console-clear-logs
Clear the MCP log cache (used by 'console-get-logs') and the Unity Editor Console window. Useful for isolating logs to a specific action by clearing the slate first.
profiler-start
Enable Unity's runtime profiler and open the Profiler window. Idempotent: calling when already enabled returns the current enabled state without error.