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 tests-rungit 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/tests-run)<a href="https://agentmods.dev/skills/ivanmurzak/unity-mcp/tests-run"><img src="https://agentmods.dev/badge/skills/ivanmurzak/unity-mcp/tests-run/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/tests-run"><img src="https://agentmods.dev/badge/skills/ivanmurzak/unity-mcp/tests-run.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 61 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00068 | $0.02495 |
| Opus 5.5 | $0.00027 | $0.00998 |
| Sonnet 5.5 | $0.00014 | $0.00499 |
| Haiku 4.5 | $0.00007 | $0.00249 |
Grade A, and why
tests-run 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 5d 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tests / Run
Execute Unity tests and return detailed results. Supports filtering by test mode, assembly, namespace, class, and method. Recommended to use 'EditMode' for faster iteration during development. Precondition: every open scene MUST be saved (no unsaved changes). If any open scene is dirty, this tool throws an InvalidOperationException listing the dirty scenes; save them and retry.
Filters
testMode(defaultEditMode) —EditModeorPlayMode. EditMode is faster; prefer it during iteration.testAssembly/testNamespace/testClass/testMethod— optional, layered filters. Namespace and class filters become regexgroupNamesso the validation count and Unity's execution stay in sync.testMethodmust be fully qualified (Namespace.FixtureName.TestName).query— RQL over thetestssource instead of the four filters: any selection, run as ONE Test Runner run, e.g.tests | where fixture == "PlayerTests" or categories contains "Smoke". One mode per run; the mode comes from the selected tests. Explore first with rql-query:tests | where fullName contains "Spline" | select fullName mode.result— RQL stages applied to the results (sourcetestResults: name status durationMs message stackTrace), e.g.where status == "Failed" | select name message; the answer is then a summary line plus compact RQL text.
Response toggles
includePassingTests(defaultfalse) — include details for passing tests; otherwise only failing test details are returned.includeMessages(defaulttrue) — include per-test result messages.includeStacktrace(defaultfalse) — include stack traces for failing tests.includeLogs(defaultfalse) — include console logs captured during the run.logType(defaultWarning) — minimum log severity to include.includeLogsStacktrace(defaultfalse) — include log stack traces (large payload; use sparingly).
Domain reloads
If the AssetDatabase refresh triggers compilation, the tool persists the run parameters to SessionState, returns Processing, and resumes the run automatically after the reload completes. Pre-existing compilation errors short-circuit the run and return the error details so the caller can fix the project first.
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.
- 5d ago Changed · +14 lines a8a5e0248bc3
- 1mo ago First seen · 280 lines · 68 tokens per session scan A 58a002db02de
tests-run is a skill published in the GitHub repository IvanMurzak/Unity-MCP (4,509 stars, last pushed yesterday), licensed Apache-2.0. It adds 68 tokens to every session and 2,495 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 2026-09-03.
Other skills, from other repositories
godot-gdscript-headless-testing
Run GDScript test suites from the command line with godot --headless, using a SceneTree/MainLoop runner script that exits non-zero on failure so CI can gate merges. Use when a Godot project needs unit tests without opening the editor, when wiring a CI job (GitHub Actions or similar) that must fail the build on a…
roblox-testing
Test, debug, or profile Roblox experiences. Use for Studio debugging, TestEZ, logging, connection cleanup, memory or network diagnostics, MicroProfiler, Scene Analysis, and Script Profiler.
gdunit-driver
Run gdUnit4 unit tests and parse results into structured output. Use this skill after writing or modifying code to verify correctness via unit tests, when diagnosing test failures, or when writing new test files. Triggers: "run tests", "test fails", "write a test", any gdUnit4/unit test mention. Supports both GDScript…
godot-testing-patterns
Expert blueprint for testing patterns using GUT (Godot Unit Test), integration tests, mock/stub patterns, async testing, and validation techniques. Covers assert patterns, signal testing, and CI/CD integration. Use when implementing tests OR validating game logic. Keywords GUT, unit test, integration test, assert…
gm-verify
Mechanical verification of the built game: headless build, unit tests, lint, static checks. Explicit invocation only — use /gm-verify.
uw-unity-test-runner
Generates EditMode and PlayMode tests using NUnit, mapped from GDD Gherkin scenarios. Use when writing tests, validating features, ensuring code quality, or verifying behavior after changes. Triggers on requests like "write tests for this", "test the health system", "add unit tests", "verify this works", "add PlayMode…