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 agentmods add rules/muammar-yacoob/unity-mcp/unity_mcp_toolsgit clone --depth 1 https://github.com/muammar-yacoob/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/rules/muammar-yacoob/unity-mcp/unity_mcp_tools)<a href="https://agentmods.dev/rules/muammar-yacoob/unity-mcp/unity_mcp_tools"><img src="https://agentmods.dev/badge/rules/muammar-yacoob/unity-mcp/unity_mcp_tools.svg" alt="Measured on agentmods" 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 | $0.00393 | $0.00393 |
| Opus 5 | $0.00197 | $0.00197 |
| Sonnet 5 | $0.00079 | $0.00079 |
| Haiku 4.5 | $0.00039 | $0.00039 |
Grade A, and why
unity_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.
What it actually says
- Reuse shared transport and services
- Instantiate
TransportFactory.create()and service singletons once perregisterToolsinvocation as in tools.ts to avoid redundant connections.
- Instantiate
- Validate parameters with zod
- Define tool schemas using
z.object({...}), marking optional values with.optional()and defaults with.default()to match existing patterns likeload_sceneandenter_playmode.
- Define tool schemas using
- Return JSON-formatted strings
- Wrap Unity responses with
JSON.stringify(result, null, 2)and map error branches tosuccess: falsepayloads for consistency across tools.
- Wrap Unity responses with
- Catch and report transport errors
- Enclose transport calls in
try/catch; on failure, respond with an error message derived fromerror instanceof Error ? error.message : String(error)mirroringexecute_csharpandget_console_logs.
- Enclose transport calls in
- Document tool capabilities inline
- Provide descriptive multi-line
descriptionfields that enumerate example usages when the tool is high impact (see theexecute_csharpblock) to guide downstream agents.
- Provide descriptive multi-line
// Adapt pattern when adding a new tool
server.addTool({
name: "refresh_assets",
description: "Trigger Unity AssetDatabase.Refresh to pick up filesystem changes.",
parameters: z.object({}),
execute: async () => {
try {
const result = await assetService.refreshAssets();
return JSON.stringify(result, null, 2);
} catch (error) {
return JSON.stringify({
success: false,
error: error instanceof Error ? error.message : String(error),
}, null, 2);
}
},
});
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 · 37 lines · 393 tokens per session scan A 313e5054b294
unity_mcp_tools is a cursor rule published in the GitHub repository muammar-yacoob/unity-mcp (4 stars, last pushed 9mo ago), licensed MIT. It adds 393 tokens to every session, about $0.0020 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 cursor rules, from other repositories
meta-quest-agentic-tools
Use Meta Quest Agentic Tools for Meta Quest and Horizon OS samples.
unity-performance
Cursor rule "unity-performance" from Common-ka/ai-agent-unity-rules, covering unity performance rules, update/fixedupdate/lateupdate, usage rules, object pooling (unityengine.pool) and addressables (not resources).
narrative-writing
游戏叙事写作助手行为约束(game-narrative-mcp).
meta-quest-agentic-tools
Use Meta Quest Agentic Tools for Meta Quest and Horizon OS samples.
00-project-overview
Base project rule — purpose, constraints, and defaults for mcp-5etools.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.