MCP 助手
- 作者仓库星标 10,292
- 作者更新于 实时读取
- 作者仓库 unity-mcp
- 领域
- AI 智能
- 兼容 Agent
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- 信任分
- 88 / 100 · 社区维护
- 作者 / 版本 / 许可
- @CoplayDev · 未声明 license
- Token 消耗评级
- 中等消耗
- 接入复杂程度
- 需简单配置
- 是否需要外部 API Key
- 不需要
- 兼容的系统
- 未声明(默认跨平台)
- 底层运行要求
- Python
- 文件与系统权限
-
- 只读
- 允许写入 / 修改
- Shell 执行
- 网络行为
- 允许外网请求
- 安装命令数
- 26 条
档案由构建时根据 SKILL.md 与安装命令自动衍生,可能与作者实际意图存在差异。
需要注意: 未限定 allowed-tools,默认拥有全部工具权限。
---
name: unity-mcp-orchestrator
description: Orchestrate Unity Editor via MCP (Model Context Protocol) tools and resources. Use when working…
category: AI 智能
runtime: Python
---
# unity-mcp-orchestrator 输出预览
## PART A: 任务判断
- 适用问题:提示词、Agent 工作流、模型评估或自动化推理。
- 输入要求:目标材料、限制条件、期望输出和验收方式。
- 证据边界:围绕“Template Notice / Quick Start: Resource-First Workflow / Critical Best Practices”读取原文规则,不把推断写成作者承诺。
## PART B: 执行结果
- **01** 任务判断:确认你的需求是否属于提示词、Agent 工作流、模型评估或自动化推理,并标出输入、限制和预期结果。
- **02** 执行计划:优先按“Template Notice / Quick Start: Resource-First Workflow / Critical Best Practices”拆成步骤,说明每一步会读取什么、修改什么、产出什么。
- **03** 交付结果:给出可复制的命令、文件改动、检查清单或内容草稿,并说明如何继续迭代。
- **04** 风险边界:结合 读取文件、写入/修改文件、执行终端命令、会按任务需要访问外部网络、通常不需要额外 API Key 给出执行前确认项。
## Running Rules
- 读取文件、写入/修改文件、执行终端命令;会按任务需要访问外部网络;通常不需要额外 API Key。
- 先小样例验证,再放大到真实任务。
- 交付时同时给结果、检查口径和下一步迭代建议。 原文没有稳定的斜杠命令要求。安装验证后通常全局生效,直接在对话里点名这个 Skill 并描述任务即可。
告诉 Agent 目标文件或材料、期望结果、不可改范围、是否允许联网或执行命令。本 Skill 的权限画像是:读取文件、写入/修改文件、执行终端命令。
先用一个小任务确认它会围绕“Template Notice / Quick Start: Resource-First Workflow / Critical Best Practices”工作;涉及文件或命令时,先看 diff、日志、预览或测试结果。
检查最终产物是否包含明确结果、必要证据和下一步动作;如果输出泛泛而谈,就补充输入、边界和验收标准后重跑。
---
name: unity-mcp-orchestrator
description: Orchestrate Unity Editor via MCP (Model Context Protocol) tools and resources. Use when working…
category: AI 智能
source: CoplayDev/unity-mcp
---
# unity-mcp-orchestrator
## 什么时候使用
- 用于组织测试、定位失败并形成修复闭环 适合处理AI Agent、提示词、模型评估与自动化推理,核心价值是把输入、判断、执行、验证和交付边界固定下来,避免 Agent 泛泛回答。 把任务拆成可执行、可检查、可继续迭代的步骤;通常不需要额外…
- 面向提示词、Agent 工作流、模型评估或自动化推理,优先处理能明确输入、步骤和验收标准的工作。
## 需要提供什么
- 目标材料、目录范围、期望结果和不可改动内容。
- 是否允许联网、执行命令、读写文件或调用外部服务。
## 执行规则
- 围绕「Template Notice / Quick Start: Resource-First Workflow / Critical Best Practices」组织步骤,不把推断写成作者事实。
- 读取文件、写入/修改文件、执行终端命令;会按任务需要访问外部网络;通常不需要额外 API Key。
- 先跑小样例,确认结果可检查后再扩大任务范围。
## 输出要求
- 给出最终产物、关键证据、验证方式和下一步动作。
- 信息不足时标记 unknown,不编造命令、平台或依赖。 作者原文负责流程事实;仓库文件负责来源和命令;流狐只补充适用场景、限制和质量判断。
skill "unity-mcp-orchestrator" {
输入层 -> 用户目标 + 目标文件 + 禁止范围 + 验收标准
上下文层 -> Template Notice / Quick Start: Resource-First Workflow / Critical Best Practices
规则层 -> SKILL.md 触发条件 / 执行顺序 / 输出格式
运行层 -> Python | 读取文件、写入/修改文件、执行终端命令 | 会按任务需要访问外部网络
安全层 -> 通常不需要额外 API Key + 小任务验证 + diff / 日志复核
输出层 -> 可复制结果 + 检查清单 + 下一步迭代
} Unity-MCP Operator Guide
This skill helps you effectively use the Unity Editor with MCP tools and resources.
Template Notice
Examples in references/workflows.md and references/tools-reference.md are reusable templates. They may be inaccurate across Unity versions, package setups (UGUI/TMP/Input System), and project-specific conventions. Please check console, compilation errors, or use screenshot after implementation.
Before applying a template:
- Validate targets/components first via resources and
find_gameobjects. - Treat names, enum values, and property payloads as placeholders to adapt.
Quick Start: Resource-First Workflow
Always read relevant resources before using tools. This prevents errors and provides the necessary context.
1. Check editor state → mcpforunity://editor/state
2. Understand the scene → mcpforunity://scene/gameobject-api
3. Find what you need → find_gameobjects or resources
4. Take action → tools (manage_gameobject, create_script, script_apply_edits, apply_text_edits, validate_script, delete_script, get_sha, etc.)
5. Verify results → read_console, manage_camera(action="screenshot"), resources
Critical Best Practices
1. After Writing/Editing Scripts: Wait for Compilation and Check Console
# After create_script or script_apply_edits:
# Both tools already trigger AssetDatabase.ImportAsset + RequestScriptCompilation automatically.
# No need to call refresh_unity — just wait for compilation to finish, then check console.
# 1. Poll editor state until compilation completes
# Read mcpforunity://editor/state → wait until is_compiling == false
# 2. Check for compilation errors
read_console(types=["error"], count=10, include_stacktrace=True)
Why: Unity must compile scripts before they're usable. create_script and script_apply_edits already trigger import and compilation automatically — calling refresh_unity afterward is redundant.
2. Use batch_execute for Multiple Operations
# 10-100x faster than sequential calls
batch_execute(
commands=[
{"tool": "manage_gameobject", "params": {"action": "create", "name": "Cube1", "primitive_type": "Cube"}},
{"tool": "manage_gameobject", "params": {"action": "create", "name": "Cube2", "primitive_type": "Cube"}},
{"tool": "manage_gameobject", "params": {"action": "create", "name": "Cube3", "primitive_type": "Cube"}}
],
parallel=True # Hint only: Unity may still execute sequentially
)
Max 25 commands per batch by default (configurable in Unity MCP Tools window, max 100). Use fail_fast=True for dependent operations.
Tip: Also use batch_execute for discovery — batch multiple find_gameobjects calls instead of calling them one at a time:
batch_execute(commands=[
{"tool": "find_gameobjects", "params": {"search_term": "Camera", "search_method": "by_component"}},
{"tool": "find_gameobjects", "params": {"search_term": "Player", "search_method": "by_tag"}},
{"tool": "find_gameobjects", "params": {"search_term": "GameManager", "search_method": "by_name"}}
])
3. Use Screenshots to Verify Visual Results
# Basic screenshot (saves to Assets/, returns file path only)
manage_camera(action="screenshot")
# Inline screenshot (returns base64 PNG directly to the AI)
manage_camera(action="screenshot", include_image=True)
# Use a specific camera and cap resolution for smaller payloads
manage_camera(action="screenshot", camera="MainCamera", include_image=True, max_resolution=512)
# Batch surround: captures front/back/left/right/top/bird_eye around the scene
manage_camera(action="screenshot", batch="surround", max_resolution=256)
# Batch surround centered on a specific object
manage_camera(action="screenshot", batch="surround", view_target="Player", max_resolution=256)
# Positioned screenshot: place a temp camera and capture in one call
manage_camera(action="screenshot", view_target="Player", view_position=[0, 10, -10], max_resolution=512)
# Scene View screenshot: capture what the developer sees in the editor
manage_camera(action="screenshot", capture_source="scene_view", include_image=True)
# Scene View framed on a specific object
manage_camera(action="screenshot", capture_source="scene_view", view_target="Canvas", include_image=True)
Best practices for AI scene understanding:
- Use
include_image=Truewhen you need to see the scene, not just save a file. - Use
batch="surround"for a comprehensive overview (6 angles, one command). - Use
view_target/view_positionto capture from a specific viewpoint without needing a scene camera. - Use
capture_source="scene_view"to see the editor viewport (gizmos, wireframes, grid). - Keep
max_resolutionat 256–512 to balance quality vs. token cost.
# Agentic camera loop: point, shoot, analyze
manage_gameobject(action="look_at", target="MainCamera", look_at_target="Player")
manage_camera(action="screenshot", camera="MainCamera", include_image=True, max_resolution=512)
# → Analyze image, decide next action
# Multi-view screenshot (6-angle contact sheet)
manage_camera(action="screenshot_multiview", max_resolution=480)
# Scene View for editor-level inspection (shows gizmos, debug overlays, etc.)
manage_camera(action="screenshot", capture_source="scene_view", view_target="Player", include_image=True)
4. Check Console After Major Changes
read_console(
action="get",
types=["error", "warning"], # Focus on problems
count=10,
format="detailed"
)
5. Always Check editor_state Before Complex Operations
# Read mcpforunity://editor/state to check:
# - is_compiling: Wait if true
# - is_domain_reload_pending: Wait if true
# - ready_for_tools: Only proceed if true
# - blocking_reasons: Why tools might fail
Parameter Type Conventions
These are common patterns, not strict guarantees. manage_components.set_property payload shapes can vary by component/property; if a template fails, inspect the component resource payload and adjust.
Vectors (position, rotation, scale, color)
# Both forms accepted:
position=[1.0, 2.0, 3.0] # List
position="[1.0, 2.0, 3.0]" # JSON string
Booleans
# Both forms accepted:
include_inactive=True # Boolean
include_inactive="true" # String
Colors
# Auto-detected format:
color=[255, 0, 0, 255] # 0-255 range
color=[1.0, 0.0, 0.0, 1.0] # 0.0-1.0 normalized (auto-converted)
Paths
# Assets-relative (default):
path="Assets/Scripts/MyScript.cs"
# URI forms:
uri="mcpforunity://path/Assets/Scripts/MyScript.cs"
uri="file:///full/path/to/file.cs"
Core Tool Categories
| Category | Key Tools | Use For |
|---|---|---|
| Scene | manage_scene, find_gameobjects |
Scene operations, finding objects |
| Objects | manage_gameobject, manage_components |
Creating/modifying GameObjects |
| Scripts | create_script, script_apply_edits, validate_script |
C# code management (auto-refreshes on create/edit) |
| Assets | manage_asset, manage_prefabs |
Asset operations. Prefab instantiation is done via manage_gameobject(action="create", prefab_path="..."), not manage_prefabs. |
| Editor | manage_editor, execute_menu_item, read_console |
Editor control, package deployment (deploy_package/restore_package actions) |
| Testing | run_tests, get_test_job |
Unity Test Framework |
| Batch | batch_execute |
Parallel/bulk operations |
| Camera | manage_camera |
Camera management (Unity Camera + Cinemachine). Tier 1 (always available): create, target, lens, priority, list, screenshot. Tier 2 (requires com.unity.cinemachine): brain, body/aim/noise pipeline, extensions, blending, force/release. 7 presets: follow, third_person, freelook, dolly, static, top_down, side_scroller. Resource: mcpforunity://scene/cameras. Use ping to check Cinemachine availability. See tools-reference.md. |
| Graphics | manage_graphics |
Rendering and post-processing management. 33 actions across 5 groups: Volume (create/configure volumes and effects, URP/HDRP), Bake (lightmaps, light probes, reflection probes, Edit mode only), Stats (draw calls, batches, memory), Pipeline (quality levels, pipeline settings), Features (URP renderer features: add, remove, toggle, reorder). Resources: mcpforunity://scene/volumes, mcpforunity://rendering/stats, mcpforunity://pipeline/renderer-features. Use ping to check pipeline status. See tools-reference.md. |
| Packages | manage_packages |
Install, remove, search, and manage Unity packages and scoped registries. Query actions: list installed, search registry, get info, ping, poll status. Mutating actions: add/remove packages, embed for editing, add/remove scoped registries, force resolve. Validates identifiers, warns on git URLs, checks dependents before removal (force=true to override). See tools-reference.md. |
| Physics | manage_physics |
Manage 3D and 2D physics (21 actions). Settings, collision matrix, materials, joints (14 types). Queries: raycast, raycast_all, linecast, shapecast (sphere/box/capsule sweep), overlap. Forces: apply_force (AddForce/AddTorque/AddExplosionForce with ForceMode). Rigidbody: get_rigidbody, configure_rigidbody (mass, drag, gravity, constraints, collision detection). Validation: scene-wide checks. Simulation: simulate_step in edit mode. See tools-reference.md. |
| ProBuilder | manage_probuilder |
3D modeling, mesh editing, complex geometry. When com.unity.probuilder is installed, prefer ProBuilder shapes over primitive GameObjects for editable geometry, multi-material faces, or complex shapes. Supports 12 shape types, face/edge/vertex editing, smoothing, and per-face materials. See ProBuilder Guide. |
| UI | manage_ui, batch_execute with manage_gameobject + manage_components |
UI Toolkit: Use manage_ui to create UXML/USS files, attach UIDocument, inspect visual trees. uGUI (Canvas): Use batch_execute for Canvas, Panel, Button, Text, Slider, Toggle, Input Field. Read mcpforunity://project/info first to detect uGUI/TMP/Input System/UI Toolkit availability. (see UI workflows) |
| Docs | unity_reflect, unity_docs |
API verification and documentation lookup. unity_reflect inspects live C# APIs via reflection (requires Unity connection): search types across assemblies, get_type for member summary, get_member for full signatures. unity_docs fetches official docs from docs.unity3d.com (no Unity connection needed): get_doc (ScriptReference), get_manual (Manual pages), get_package_doc (package docs), lookup (parallel search all sources + project assets). Trust hierarchy: reflection > project assets > docs. Workflow: unity_reflect search -> get_type -> get_member -> unity_docs lookup. See tools-reference.md. |
Common Workflows
Creating a New Script and Using It
# 1. Create the script (automatically triggers import + compilation)
create_script(
path="Assets/Scripts/PlayerController.cs",
contents="using UnityEngine;\n\npublic class PlayerController : MonoBehaviour\n{\n void Update() { }\n}"
)
# 2. Wait for compilation to finish
# Read mcpforunity://editor/state → wait until is_compiling == false
# 3. Check for compilation errors
read_console(types=["error"], count=10)
# 4. Only then attach to GameObject
manage_gameobject(action="modify", target="Player", components_to_add=["PlayerController"])
Finding and Modifying GameObjects
# 1. Find by name/tag/component (returns IDs only)
result = find_gameobjects(search_term="Enemy", search_method="by_tag", page_size=50)
# 2. Get full data via resource
# mcpforunity://scene/gameobject/{instance_id}
# 3. Modify using the ID
manage_gameobject(action="modify", target=instance_id, position=[10, 0, 0])
Running and Monitoring Tests
# 1. Start test run (async)
result = run_tests(mode="EditMode", test_names=["MyTests.TestSomething"])
job_id = result["job_id"]
# 2. Poll for completion
result = get_test_job(job_id=job_id, wait_timeout=60, include_failed_tests=True)
Pagination Pattern
Large queries return paginated results. Always follow next_cursor:
cursor = 0
all_items = []
while True:
result = manage_scene(action="get_hierarchy", page_size=50, cursor=cursor)
all_items.extend(result["data"]["items"])
if not result["data"].get("next_cursor"):
break
cursor = result["data"]["next_cursor"]
Multi-Instance Workflow
When multiple Unity Editors are running:
# 1. List instances via resource: mcpforunity://instances
# 2. Set active instance
set_active_instance(instance="MyProject@abc123")
# 3. All subsequent calls route to that instance
Error Recovery
| Symptom | Cause | Solution |
|---|---|---|
| Tools return "busy" | Compilation in progress | Wait, check editor_state |
| "stale_file" error | File changed since SHA | Re-fetch SHA with get_sha, retry |
| Connection lost | Domain reload | Wait ~5s, reconnect |
| Commands fail silently | Wrong instance | Check set_active_instance |
Reference Files
For detailed schemas and examples:
- tools-reference.md: Complete tool documentation with all parameters
- resources-reference.md: All available resources and their data
- workflows.md: Extended workflow examples and patterns
先判断是否适合
作者设计意图
作者的方法与取舍
边界和复核