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_transportgit 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_transport)<a href="https://agentmods.dev/rules/muammar-yacoob/unity-mcp/unity_transport"><img src="https://agentmods.dev/badge/rules/muammar-yacoob/unity-mcp/unity_transport.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 | $0.00385 | $0.00385 |
| Opus 5 | $0.00192 | $0.00192 |
| Sonnet 5 | $0.00077 | $0.00077 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
unity_transport 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
- Use
TransportFactory.createfor runtime selection- Honour
UNITY_MCP_TRANSPORT,UNITY_MCP_HTTP_PORT,UNITY_MCP_WS_PORT, andUNITY_MCP_TIMEOUTenvironment variables as illustrated in factory.ts; avoid hard-coding ports elsewhere.
- Honour
- Surface connection diagnostics via stderr
- Log chosen transport and reconnect attempts with
console.errorfollowing the patterns in factory.ts and websocket.ts to keep MCP output channels clean.
- Log chosen transport and reconnect attempts with
- Wrap transport failures with actionable errors
- Convert axios and WebSocket failures into descriptive
Errorinstances (seeHttpTransport.requestandWebSocketTransport.handleMessage) so upstream services can compose user-friendly responses.
- Convert axios and WebSocket failures into descriptive
- Guard WebSocket lifecycle transitions
- Reuse the
connectpromise and reject pending requests on disconnect before retrying, mirroring the state machine in websocket.ts when extending behaviour.
- Reuse the
- Keep
ITransportcontract intact- Ensure new transports implement the same
request,isConnected,connect,disconnect, andgetTypemethods defined in ITransport.ts for drop-in compatibility.
- Ensure new transports implement the same
const transport = TransportFactory.create({ type: 'http', timeout: 15000 });
await transport.connect();
const result = await transport.request("/asset/refresh", {});
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 · 23 lines · 385 tokens per session scan A f7c21f9f68c9
unity_transport is a cursor rule published in the GitHub repository muammar-yacoob/unity-mcp (4 stars, last pushed 9mo ago), licensed MIT. It adds 385 tokens to every session, about $0.0019 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
08-client-server
IF 判断当前环境是否为客户端 → FabricLoader.getInstance().getEnvironmentType() == EnvType.CLIENT → World.isClient（Yarn 字段；yarn 1.14.4 World.mapping）。不要用 MCP/Forge 的 isRemote.
07-datagen
IF 生成物品/方块模型 JSON → 手动编写 JSON 在 src/main/resources/assets/{modid}/models/.
meta-quest-agentic-tools
Use Meta Quest Agentic Tools for Meta Quest and Horizon OS samples.
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.
visual-and-observational-rules
Defines the visual aspects of the game and how the player observes the world. This includes map color-coding, screen effects, and the overall simulation style.