Unity-MCP-Server: Instructions file for Kiro

.kiro/steering/project-context.md

Unity-MCP-Server project-context.md is an instructions file for Kiro from yangfch3/Unity-MCP-Server. It costs 902 tokens per session, scanned A, original, MIT.

Project context for a Unity MCP Server, including its Unity version, C# structure, connection method, and rules for calling Unity APIs.

In plain words
What is it for?
Use it when adding or changing MCP tools, server code, protocol handling, editor UI, or other parts of this Unity package.
Why use it?
It gives an agent the background needed to make compatible changes and avoid violating the server's threading and package constraints.

Instructions file for Kiro

Written for Kiro: installed under .kiro/.

This is yangfch3/Unity-MCP-Server's own configuration. It tells Kiro how to work on Unity-MCP-Server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Unity-MCP-Server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to yangfch3/Unity-MCP-Server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/yangfch3/Unity-MCP-Server/main/.kiro/steering/project-context.md
Clone the repo
git clone --depth 1 https://github.com/yangfch3/Unity-MCP-Server

Made for: Kiro.

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-Server project-context.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/yangfch3/unity-mcp-server/project-context/github.svg)](https://agentmods.dev/instructions/yangfch3/unity-mcp-server/project-context)
Your own site
<a href="https://agentmods.dev/instructions/yangfch3/unity-mcp-server/project-context"><img src="https://agentmods.dev/badge/instructions/yangfch3/unity-mcp-server/project-context/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.

agentmods 80×15 button for Unity-MCP-Server project-context.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/yangfch3/unity-mcp-server/project-context"><img src="https://agentmods.dev/badge/instructions/yangfch3/unity-mcp-server/project-context.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 902 This file is loaded in full into every session.
When invoked 902 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00902 $0.00902
Opus 5 $0.00451 $0.00451
Sonnet 5 $0.00180 $0.00180
Haiku 4.5 $0.00090 $0.00090

Measured 2d ago against content hash de065ae4f020, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

Unity-MCP-Server project-context.md 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 2d 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.

.kiro/steering/project-context.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Unity MCP Server — Project Context

Project Overview

MCP (Model Context Protocol) server plugin for Unity Editor, distributed as a Unity Package. Allows external AI Agents to access Unity Editor capabilities via the standard MCP protocol.

Tech Stack

  • C# / Unity 2022.3+
  • Editor assembly only (does not affect runtime builds)
  • Streamable HTTP transport (MCP 2025-03-26 spec)
  • No external dependencies (built-in MiniJson replaces Newtonsoft.Json)

Code Structure

Editor/
├── Core/       # IMcpTool interface, ToolResult, ToolRegistry
├── Protocol/   # JsonRpcDispatcher, MiniJson
├── Server/     # McpServer, McpServerManager, MainThreadQueue
├── Tools/      # Built-in tools (debug/editor/build categories), includes shared helpers (*Helper.cs)
└── UI/         # ConfigPanel EditorWindow

Key Design Constraints

  • All Unity API calls must execute on the main thread (dispatched via MainThreadQueue)
  • All IMcpTool.Execute calls are already dispatched to the main thread by JsonRpcDispatcher via MainThreadQueue; tool implementations do not need to handle thread dispatch internally
  • HttpListener runs on a background thread
  • Adding a new tool only requires implementing the IMcpTool interface; ToolRegistry auto-discovers via reflection
  • After Domain Reload, the service auto-recovers using an EditorPrefs flag
  • Namespace: UnityMcp.Editor, tool sub-namespace: UnityMcp.Editor.Tools

Unity MCP Tool Usage Guidelines

  • NEVER call build_compile or build_runTests during a multi-task execution or coding session. These tools trigger Domain Reload, which aborts the MCP server's HTTP thread and breaks the current connection. If compilation or test verification is needed, place it as the very last step of the entire session.
  • For incremental code validation during implementation, use getDiagnostics (IDE static analysis) instead of build_compile. It does not trigger Domain Reload.
  • When build_compile or build_runTests returns a connection error (e.g., "fetch failed"), it is likely due to Domain Reload. Wait briefly and retry once if needed.

Read the full file on GitHub · 72 lines

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. 2d ago First seen · 72 lines · 902 tokens per session scan A de065ae4f020

Subscribe to this mod's changes

Unity-MCP-Server project-context.md is an instructions file published in the GitHub repository yangfch3/Unity-MCP-Server (6 stars, last pushed 2d ago), licensed MIT. It adds 902 tokens to every session, about $0.0045 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 2026-09-10.

Related

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,126 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens