Unity-MCP connects AI coding agents to the Unity game engine through MCP, letting them work with the Unity Editor and running games. It is used by game developers to generate code, automate development and testing, debug projects, and add AI-driven behavior to games. The catalogue entries provide skills, instructions, an MCP integration, and settings for operating this workflow.
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 skills/ivanmurzak/unity-mcp/scene-get-datanpx skills add IvanMurzak/Unity-MCP --skill scene-get-datagit clone --depth 1 https://github.com/IvanMurzak/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/skills/ivanmurzak/unity-mcp/scene-get-data)<a href="https://agentmods.dev/skills/ivanmurzak/unity-mcp/scene-get-data"><img src="https://agentmods.dev/badge/skills/ivanmurzak/unity-mcp/scene-get-data.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 5.1 | $0.00064 | $0.03429 |
| Opus 5 | $0.00032 | $0.01715 |
| Sonnet 5 | $0.00013 | $0.00686 |
| Haiku 4.5 | $0.00006 | $0.00343 |
Grade A, and why
scene-get-data 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.
How it starts
The opening of the file, as written. The whole thing — 432 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scene / Get Data
This tool retrieves the list of root GameObjects in the specified scene. Use 'scene-list-opened' tool to get the list of all opened scenes.
Toggles (all default false to keep responses small)
includeRootGameObjects— include root GameObjects in the scene data.includeChildrenDepth(default 3) — depth of the hierarchy to include.includeBounds— include 3D bounds for GameObjects.includeData— include serialized component data for GameObjects.
Path-scoped reads (token-saving)
Supply paths to read only the listed fields/elements from the scene's root-GameObjects array via Reflector.TryReadAt, or viewQuery to navigate/filter the same array via Reflector.View. The result populates Data on the returned SceneData. These two parameters are mutually exclusive.
Path syntax
fieldName, nested/field, arrayField/[i], dictField/[key]. Leading #/ is stripped. Example: paths=['[0]/name'] reads the name of the first root GameObject.
How to Call
unity-mcp-cli run-tool scene-get-data --input '{
"openedSceneName": "string_value",
"includeRootGameObjects": false,
"includeChildrenDepth": 0,
"includeBounds": false,
"includeData": false,
"paths": "string_value",
"viewQuery": "string_value"
}'
For complex input (multi-line strings, code), save the JSON to a file and use:
unity-mcp-cli run-tool scene-get-data --input-file args.jsonOr pipe via stdin (recommended):
unity-mcp-cli run-tool scene-get-data --input-file - <<'EOF' {"param": "value"} EOF
Troubleshooting
If unity-mcp-cli is not found, either install it globally (npm install -g unity-mcp-cli) or use npx unity-mcp-cli instead.
Read the /unity-initial-setup skill for detailed installation instructions.
Input
| Name | Type | Required | Description |
|---|---|---|---|
openedSceneName |
string |
No | Name of the opened scene. If empty or null, the active scene will be used. |
includeRootGameObjects |
boolean |
No | If true, includes root GameObjects in the scene data. |
includeChildrenDepth |
integer |
No | Determines the depth of the hierarchy to include. |
includeBounds |
boolean |
No | If true, includes bounding box information for GameObjects. |
includeData |
boolean |
No | If true, includes component data for GameObjects. |
paths |
any |
No | Optional. List of paths to read individually via Reflector.TryReadAt against the scene's root-GameObjects array. Path syntax: 'fieldName', '[i]/field', '[i]/component/[j]/property'. Mutually exclusive with 'viewQuery'. |
viewQuery |
any |
No | Optional. View-query filter routed through Reflector.View on the scene's root-GameObjects array. Mutually exclusive with 'paths'. |
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.
- 2d ago First seen · 432 lines · 64 tokens per session scan A 7a9ee2dc5d45
scene-get-data is a skill published in the GitHub repository IvanMurzak/Unity-MCP (4,148 stars, last pushed yesterday), licensed Apache-2.0. It adds 64 tokens to every session and 3,429 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
unity-mcp-orchestrator
Orchestrate Unity Editor via MCP (Model Context Protocol) tools and resources. Use when working with Unity projects through MCP for Unity - creating/modifying GameObjects, editing scripts, managing scenes, running tests, or any Unity Editor automation. Provides best practices, tool schemas, and workflow patterns for…
blender-to-unity
Hand off a model from Blender (via BlenderMCP) into Unity (via MCP for Unity) — export the current Blender model, import it through importmodelfile, and place it in the open scene. Use when the user has BlenderMCP and MCP for Unity both connected and wants to bring a Blender model into Unity. Does NOT drive Blender's…
mcp-source
Switch MCP for Unity package source in connected Unity projects. Use /mcp-source [main|beta|branch|local] to swap between upstream releases, your remote branch, or local dev checkout.
executing-csharp-scripts-in-unity-editor
Use this skill always when you need to use executecsharpscriptinunityeditor tool to modify scenes, add, remove or modify game objects, components, scriptable objects or perform any other task in Unity Editor using C# scripts. Also covers when and how to use readunityconsolelogs and rununitytests tools as part of the…
unity-game-player
Autonomous Unity game-playing skill for AI agents. Provides the complete closed-loop workflow (INIT → SENSE+COMPUTE → ACT → REPEAT) for dynamically discovering game mechanics, reading live state via C# script execution, computing mathematically precise actions, and simulating player input. Use when an agent must play…
creating-python-scripts
Use when creating or editing a Python script, utility, CLI helper, one-off automation, or small standalone Python program that should stay as a script instead of becoming a multi-file project.