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 makifbaysal/tasktrooper --skill game-engine-mcp-toolsgit clone --depth 1 https://github.com/makifbaysal/tasktrooperWrote 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/makifbaysal/tasktrooper/game-engine-mcp-tools)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/game-engine-mcp-tools"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/game-engine-mcp-tools/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/makifbaysal/tasktrooper/game-engine-mcp-tools"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/game-engine-mcp-tools.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 | $0.00077 | $0.02001 |
| Opus 5.5 | $0.00031 | $0.00800 |
| Sonnet 5.5 | $0.00015 | $0.00400 |
| Haiku 4.5 | $0.00008 | $0.00200 |
Grade A, and why
game-engine-mcp-tools 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 4d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Game Engine MCP Tools
Overview
The user can connect live editors to you through MCP servers in Settings → MCP servers. They are optional and disabled by default. When one is connected you can look inside a running editor — scene hierarchy, console errors, test runs, screenshots — which is often the only way to observe an engine game on this machine. When none is connected, nothing changes: the headless commands (game-build-check, game-visual-self-review) are the path.
Core principle: An editor MCP is an extra pair of eyes, never the verdict. The repository's tests, run in this task, decide; the MCP shows you what the build and the tests cannot.
Is it there?
Look at your tool list. A connected server's tools appear there (in CLI runtimes as mcp__<server>__<tool>, e.g. tools under unity, godot, unreal, blender, browser). No tools from it → it is not connected.
- Never ask the user to install, enable or start an editor or MCP server mid-task. Fall back to the headless CLI and say in the closing message what you could not observe.
- A tool call that fails because the editor is closed or busy is a finding, not something to retry in a loop.
First call: is the editor on your workspace?
Editor MCP servers talk to whatever editor the user has open. That may be their main checkout, another branch, or another project — not your task workspace. Before trusting anything it shows, ask it for the open project's path (editor/project info) and compare with your working directory.
- Different path → its scenes, console and tests describe someone else's code. Do not edit through it; use the CLI instead, and note it in the closing message.
- Same path → it sees your files once the editor has refreshed or recompiled them; trigger or wait for that before reading the console or running tests.
What each server is for
| Server | What it is | Use it to | Watch out for |
|---|---|---|---|
unity |
MCP for Unity (CoplayDev/unity-mcp); needs its package in the project and the Editor open | Inspect scenes and GameObjects (manage_scene), read console errors and compile errors (read_console), run EditMode/PlayMode tests in the open editor (run_tests), control play mode and editor state (manage_editor), capture editor/game views |
An open Editor locks the project, so a batchmode CLI run on the same project fails — run the tests through the MCP instead, and still read their results. UNITY_MCP_DEFAULT_INSTANCE picks the editor when several are open. |
godot |
Godot AI (hi-godot/godot-ai); needs the addons/godot_ai addon and the editor open |
Inspect the scene tree and nodes, read scripts and validation errors, run the project or a scene, read debugger/output errors, run the test suite | The server version must equal the project's addon version, or it refuses to attach. Its server uses port 8000. |
unreal |
Epic's built-in Unreal MCP (UE 5.8+, "Unreal MCP" plugin, Experimental), loopback HTTP on 127.0.0.1:8000 | Inspect actors, components and assets in the open level; run editor Python and automation commands; check what is placed where | Experimental: tool shapes can change between engine versions. Same port 8000 as Godot AI — only one of the two can run. No authentication: anything on this machine can call it. |
blender |
MCP for Blender | Inspect and edit models, materials and renders; export assets for the game | execute_blender_code runs arbitrary Python inside Blender with the user's permissions. |
browser / built-in browser tools |
Browser automation | Load a web game, screenshot it at two viewports | See game-visual-self-review for the exact calls. |
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.
- 4d ago First seen · 85 lines · 77 tokens per session scan A 64bd262ef151
game-engine-mcp-tools is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 77 tokens to every session and 2,001 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-09.
Other skills, from other repositories
i4h-workflow-train-rl
Use when training, evaluating, or exporting Workflow policies with online RSL-RL or RLinf, including RL checkpoint and Workflow handoff.
openclaw-plugin
You are an autonomous agent in a persistent world. Your character is in SOUL.md. World rules are in WORLD.md.
ramp
Fetch and follow Ramp's published agent playbooks inside Paperclip, with mandatory approval gates for spend, incorporation, cards, account setup, and other financial actions.
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
agent-topology-optimizer
Agent skill for topology-optimizer - invoke with $agent-topology-optimizer.
paperclip-task-bridge
Create, comment on, update, and list Paperclip tasks from Hermes using scoped Paperclip API credentials.