Unity-MCP connects AI coding agents to the Unity game engine through MCP, letting them work with the Unity Editor and running games. It is used by game developers to generate code, automate development and testing, debug projects, and add AI-driven behavior to games. The catalogue entries provide skills, instructions, an MCP integration, and settings for operating this workflow.
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 IvanMurzak/Unity-MCP --skill unity-rqlgit clone --depth 1 https://github.com/IvanMurzak/Unity-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/ivanmurzak/unity-mcp/unity-rql)<a href="https://agentmods.dev/skills/ivanmurzak/unity-mcp/unity-rql"><img src="https://agentmods.dev/badge/skills/ivanmurzak/unity-mcp/unity-rql/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/ivanmurzak/unity-mcp/unity-rql"><img src="https://agentmods.dev/badge/skills/ivanmurzak/unity-mcp/unity-rql.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 | $0.00082 | $0.02158 |
| Opus 5.5 | $0.00033 | $0.00863 |
| Sonnet 5.5 | $0.00016 | $0.00432 |
| Haiku 4.5 | $0.00008 | $0.00216 |
Grade A, and why
unity-rql 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 today.
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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RQL — query and change the Unity Editor
RQL is one pipeline language for the whole Editor: find objects, read members, filter, aggregate, and change them in one call. Prefer one precise query over many exploratory calls.
rql-query— read-only queries, compact table results.rql-mutate— queries ending withset/call; all-or-nothing, undoable (Ctrl+Z),dry_run: truepreviews.rql-schema— sources and component types in the scene;rql-schema(type)lists one type's members and methods.
unity-mcp-cli run-tool rql-query --input '{"query": "objects | where name contains \"Enemy\" | select $ref name"}'
unity-mcp-cli run-tool rql-mutate --input '{"query": "objects | where name == \"Player\" | set active = false"}'
Language
RQL: source | stage | stage ...
Sources: objects (every GameObject in the loaded scenes, inactive included), roots, scenes, selection, prefab (the prefab open in prefab editing mode), console (Editor log entries), shaders, componentTypes, profiler (memory / rendering / frame snapshots; call Start / Stop / Save), tests (test methods; run a selection with tests-run query), testResults (last run), editor (Editor state and operations). Assets: unity.assets("t:Material") or unity.assets("t:Prefab", "Assets/Enemies"), unity.asset("Assets/Mats/Red.mat"). ref("Light#1234") resolves a $ref; unity.find("Player") or unity.find("Level/Pillar_1") a GameObject by unique name or path.
Stages:
where <predicate> filter
select a b.c alias=(expr) project columns (wrap computed expressions in parentheses)
sort <expr> [desc], ... stable sort
first N | skip N | count
get <path> replace each item by a member (lists are flattened)
recurse children [max-depth=N] [include-self=false] walk the hierarchy (input items included by default)
distinct [expr] | group-by expr | sum expr | min expr | max expr | avg expr
Expressions: == != < <= > >= and or not + - * / %; contains, starts-with, ends-with (case-insensitive); matches "regex"; x in [a, b]; x is null; x is not null; $ is Light (includes subclasses); has(member). Literals: numbers, "strings", true/false/null, lists [a, b], objects {x: 1, y: 2}.
Paths: a.b.c, list[0], map["key"]; .member on a list maps over its elements. List methods: .any(pred) .all(pred) .count([pred]) .sum(e) .min(e) .max(e) .first([pred]); inside them bare names refer to the element, falling back to the outer item.
Meta: $ (current item), $ref (stable id such as Light#1234), $type, $path, $index, $depth. Enums compare to strings (type == "Spot"); == on strings is case-sensitive.
Unity: GameObject has components (list), children (list), active, name, tag, layer, transform (position, localPosition, eulerAngles, localScale, parent). Component members are the C# members (public + [SerializeField]); find them via objects | get components | where $ is Light. Vectors/colors print as (x, y, z); write "(1, 2, 3)", [1, 2, 3] or {x: 1, y: 2, z: 3}; colors also "#ff8800". Material shader properties: properties["_Color"]. Destroyed objects read as null (missing references: where target == null). Navigate with paths or get; select only projects output columns.
Results come back as compact rows (header line, then col|col). Long results are truncated — refine with where/first or use count. Unknown members produce warnings with suggestions; rql-schema(type) lists a type's members.
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.
- today First seen · 99 lines · 82 tokens per session scan A da5b81e7176a
unity-rql is a skill published in the GitHub repository IvanMurzak/Unity-MCP (4,475 stars, last pushed today), licensed Apache-2.0. It adds 82 tokens to every session and 2,158 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 2026-10-16.
Other skills, from other repositories
unity-addressables
Use Addressables with explicit grouping, loading, update, and fallback rules instead of ad hoc content loading.
unity-build-release
Run Unity builds, CI, and release packaging with reproducible configuration and platform-aware checks.
unity-csharp-standards
Apply Unity-specific C# standards that preserve readability, testability, and safe engine integration.
unity-editor-tooling
Create Unity editor tools that make content production safer, faster, and less dependent on tribal knowledge.
unity-gameplay-patterns
Use common Unity gameplay architecture patterns without hiding ownership inside scenes or inspector wiring.
unity-input-system
Implement Unity input with explicit action maps, device support, and UI/gameplay separation.