unity_mcp_tools

unity_mcp_tools is a cursor rule for Cursor from muammar-yacoob/unity-mcp. It costs 393 tokens per session, scanned A, original, MIT.

A set of coding rules for registering Unity tools with FastMCP, a framework for exposing functions to an AI agent. Unity is a game-development platform.

In plain words
What is it for?
Use it when adding or updating Unity MCP tools, such as tools that refresh assets, load scenes, run code, or read console logs.
Why use it?
It keeps tools consistent in how they validate inputs, share services, return results, document behavior, and report errors.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/muammar-yacoob/unity-mcp/unity_mcp_tools
Clone the repo
git clone --depth 1 https://github.com/muammar-yacoob/unity-mcp

Made for: Cursor.

Wrote 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.

agentmods badge for unity_mcp_tools

README.md
[![agentmods](https://agentmods.dev/badge/rules/muammar-yacoob/unity-mcp/unity_mcp_tools.svg)](https://agentmods.dev/rules/muammar-yacoob/unity-mcp/unity_mcp_tools)
Your own site
<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>
Per session 393 This file is loaded in full into every session.
When invoked 393 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 4d ago against content hash 313e5054b294, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.cursor/rules/unity_mcp_tools.mdc · 37 lines

What it actually says

  • Reuse shared transport and services
    • Instantiate TransportFactory.create() and service singletons once per registerTools invocation as in tools.ts to avoid redundant connections.
  • Validate parameters with zod
    • Define tool schemas using z.object({...}), marking optional values with .optional() and defaults with .default() to match existing patterns like load_scene and enter_playmode.
  • Return JSON-formatted strings
    • Wrap Unity responses with JSON.stringify(result, null, 2) and map error branches to success: false payloads for consistency across tools.
  • Catch and report transport errors
    • Enclose transport calls in try/catch; on failure, respond with an error message derived from error instanceof Error ? error.message : String(error) mirroring execute_csharp and get_console_logs.
  • Document tool capabilities inline
    • Provide descriptive multi-line description fields that enumerate example usages when the tool is high impact (see the execute_csharp block) to guide downstream agents.
// 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);
    }
  },
});
Changes

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.

  1. 4d ago First seen · 37 lines · 393 tokens per session scan A 313e5054b294

Subscribe to this mod's changes

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.