Unity AI Bridge MCP Server
io.github.butterlatte-zhang/unity-ai-bridge
Remote-control Unity Editor from any AI IDE via file-based IPC with 65 tools, zero dependencies.
What is the Unity AI Bridge MCP server?
Unity AI Bridge is an MCP server that gives AI coding assistants full remote access to the Unity Editor through file-based inter-process communication. It exposes 65 tools across 15 categories—Scene, GameObject, Assets, Prefab, Script, Profiler, and more—enabling AI agents to inspect scenes, modify objects, run tests, and profile performance without network ports or external dependencies.
Unity AI Bridge bridges the gap between AI coding assistants and the Unity Editor. While most AI tools can only read and write files, this server lets Claude, Cursor, Copilot, and other IDEs directly control the editor, inspect game state at runtime, take screenshots, run playtests, and execute custom tools. It uses file-based IPC instead of network sockets, making it reliable across recompilation and editor restarts.
How to install Unity AI Bridge
Copy-paste configuration for popular MCP clients.
No machine-readable install method is published for this server in the registry. Check the repository or website for setup instructions.
Tools & capabilities
Tools this server exposes to the agent.
scene-open— Open a scene by pathscene-save— Save the current scenescene-create— Create a new scenescene-list-opened— List all opened scenesscene-get-data— Get scene datascene-set-active— Set active scenescene-unload— Unload a scenegameobject-find— Find GameObjects by name or taggameobject-create— Create a new GameObjectgameobject-destroy— Destroy a GameObjectgameobject-modify— Modify GameObject propertiesgameobject-duplicate— Duplicate a GameObjectgameobject-set-parent— Set parent of a GameObjectgameobject-component-add— Add a component to a GameObjectgameobject-component-destroy— Remove a component from a GameObjectgameobject-component-get— Get component datagameobject-component-list-all— List all components on a GameObjectgameobject-component-modify— Modify component propertiesassets-find— Find assets by name or typeassets-find-built-in— Find built-in assets
Use cases
- Automate game testing: write AI-driven playtests that enter Play Mode, trigger actions, observe state, and verify behavior in closed loops
- Inspect and modify scenes programmatically: find GameObjects, adjust components, materials, and prefabs without manual editor interaction
- Profile and optimize performance: capture profiler snapshots, analyze hotpaths, and track garbage collection from your AI assistant
- Generate and manage assets: create materials, shaders, prefabs, and folders; search and organize your asset database
- Debug compilation and runtime errors: read console logs, execute scripts, and query runtime state to validate changes before committing
Unity AI Bridge MCP server FAQ
Unity AI Bridge is an MCP server that lets AI coding assistants (Claude, Cursor, Copilot, etc.) remotely control the Unity Editor. It exposes 65 tools for scene management, GameObject manipulation, asset handling, profiling, testing, and more—all via file-based IPC with zero external dependencies.
Yes. Unity AI Bridge is open-source under the Apache License 2.0.
Install the Unity package via Package Manager (git URL: https://github.com/butterlatte-zhang/unity-ai-bridge.git?path=Packages/com.aibridge.unity), copy the `.claude/` folder to your project root, then configure your IDE per the setup guide at https://github.com/butterlatte-zhang/unity-ai-bridge/blob/main/docs/SETUP.md. The project includes AI-native setup instructions you can send directly to your assistant.
No. Unity AI Bridge uses file-based IPC (polling) on your local machine, scoped to your user's temp directory. No ports, no firewalls, no network listeners—it just works.
Unity 2022.3 LTS and later, including Unity 6. Supports Built-in, URP, and HDRP render pipelines on Windows and macOS.
Yes. Expose any static method with the `[BridgeTool]` attribute—no registration code needed. The bridge auto-discovers and auto-documents tools at Editor startup.
README (reference)
Source of truth, from the repository.
Unity AI Bridge
Remote-control the Unity Editor from any AI IDE — no ports, no dependencies, just works.
https://github.com/user-attachments/assets/4e8b3f85-b209-406f-a96e-f8b8eddc9160
Why Unity AI Bridge?
Most AI coding assistants can read and write files, but they are blind to the Unity Editor — they can't inspect your scene, tweak materials, run tests, or profile performance. Unity AI Bridge gives AI full editor access.
Key Advantages
- 65 tools, 15 categories — Scene, GameObject, Assets, Prefab, Script, Profiler, LightProbe, Screenshot, Runtime, Tests, and more. Covers the full editor workflow, not just file I/O.
- File-based IPC, not WebSocket — No open ports, no firewall issues, no connection drops. Survives recompilation, play-mode transitions, and editor restarts gracefully.
- Zero external dependencies — Pure Python stdlib CLI/MCP server, self-contained C# Unity package. No pip install, no npm, no Node.js runtime.
- Every major AI IDE — Claude Code (Skill mode), Cursor, GitHub Copilot, Windsurf, Claude Desktop (MCP mode). One Unity plugin, all IDEs.
- 5-line extensibility — Add custom tools with
[BridgeTool]attribute. Auto-discovered, auto-serialized, auto-documented. No registration code needed. - Production-tested — Built for and battle-tested in a large-scale open-world Unity game (50+ developers, 2M+ lines of C#).
vs Unity 6 AI Gateway
Unity 6.2 introduced an official AI Gateway with MCP support. Both projects share the same goal — giving AI agents editor access via MCP — but differ in important ways:
| Unity AI Bridge | Unity 6 AI Gateway | |
|---|---|---|
| Unity version | 2022.3 LTS+ | 6.2+ only |
| Tool coverage | 65 tools across 15 categories | General-purpose (Scene, Assets, Script, Console) |
| Deep tooling | Profiler (snapshot, hotpath, stream), LightProbe, Reflection, Package Manager | Not yet available |
| IPC mechanism | File polling (~100ms) | Unix Socket / Named Pipe |
| Extensibility | [BridgeTool] attribute — 5 lines | TBD |
In practice, the ~100ms file-polling latency is imperceptible because AI agent think-time dominates each round trip. File IPC also makes cross-process debugging trivial — just inspect the JSON files on disk.
Quick Start
AI-native project — Copy the prompt below and send it to your AI coding assistant. The setup guide is written for AI to follow — you don't need to run any commands yourself.
Help me install Unity AI Bridge by following this guide: https://github.com/butterlatte-zhang/unity-ai-bridge/blob/main/docs/SETUP.md
If you prefer manual setup:
-
Unity Package — In Unity: Window > Package Manager > + > Add package from git URL:
https://github.com/butterlatte-zhang/unity-ai-bridge.git?path=Packages/com.aibridge.unityOr manually copy
Packages/com.aibridge.unityfrom this repo into your project'sPackages/directory. -
IDE Integration — Copy
.claude/to your project root, then configure your IDE per docs/SETUP.md.
Supports: Claude Code (Skill mode), Cursor, GitHub Copilot, Windsurf, Claude Desktop (MCP mode).
Tool Categories
65 tools organized into 15 categories:
| Category | Count | Tools |
|---|---|---|
| Scene | 7 | scene-open, scene-save, scene-create, scene-list-opened, scene-get-data, scene-set-active, scene-unload |
| GameObject | 11 | gameobject-find, gameobject-create, gameobject-destroy, gameobject-modify, gameobject-duplicate, gameobject-set-parent, gameobject-component-add, gameobject-component-destroy, gameobject-component-get, gameobject-component-list-all, gameobject-component-modify |
| Assets | 11 | assets-find, assets-find-built-in, assets-get-data, assets-modify, assets-move, assets-copy, assets-delete, assets-create-folder, assets-refresh, assets-material-create, assets-shader-list-all |
| Prefab | 5 | assets-prefab-create, assets-prefab-open, assets-prefab-save, assets-prefab-close, assets-prefab-instantiate |
| Script | 4 | script-read, script-update-or-create, script-delete, script-execute |
| Object | 2 | object-get-data, object-modify |
| Editor | 4 | editor-application-get-state, editor-application-set-state, editor-selection-get, editor-selection-set |
| Reflection | 2 | reflection-method-find, reflection-method-call |
| Screenshot | 1 | screenshot-capture |
| Runtime | 2 | runtime-query, runtime-invoke |
| Console | 1 | console-get-logs |
| Profiler | 5 | profiler-snapshot, profiler-stream, profiler-frame-hierarchy, profiler-hotpath, profiler-gc-alloc |
| Package | 4 | package-list, package-search, package-add, package-remove |
| Light Probe | 5 | lightprobe-generate-grid, lightprobe-analyze, lightprobe-bake, lightprobe-clear, lightprobe-configure-lights |
| Tests | 1 | tests-run |
Architecture
┌──────────────────────────────────────────────────┐
│ AI IDE │
│ (Claude Code / Cursor / Copilot / Windsurf) │
└──────────┬────────────────────┬──────────────────┘
│ │
Skill mode MCP mode
│ │
▼ ▼
┌─────────────┐ ┌──────────────┐
│ bridge.py │ │ mcp_server.py│
│ (Python) │ │ (Python) │
└──────┬──────┘ └──────┬───────┘
│ │
└────────┬─────────┘
│
File-based IPC
(request / response)
│
▼
┌───────────────────────────────┐
│ Unity Editor Plugin │
│ (com.aibridge.unity) │
│ │
│ BridgePlugin ← polls files │
│ BridgeToolRegistry │
│ BridgeToolRunner │
│ [BridgeTool] methods │
└───────────────────────────────┘
Dual-channel design: The same Unity plugin serves both Skill mode (direct CLI) and MCP mode (protocol server). Both channels communicate through the same file-based IPC — a pair of request/response files on disk. No network sockets, no port conflicts, no firewall rules.
Why file IPC? Unity's main thread is single-threaded and blocks during domain reload. File polling is the most reliable way to survive recompilation, play-mode transitions, and Editor restarts without losing messages.
Beyond Editing — AI as Game Tester
Most Unity AI tools stop at file editing. Unity AI Bridge goes further — it turns Claude Code (or any AI IDE) into a game testing harness.
| Capability | Traditional AI | With Unity AI Bridge |
|---|---|---|
| Write C# code | :white_check_mark: | :white_check_mark: |
| Check compilation errors | :x: | :white_check_mark: console-get-logs |
| Enter / exit Play Mode | :x: | :white_check_mark: editor-application-set-state |
| Trigger game actions | :x: | :white_check_mark: runtime-invoke |
| Read runtime game state | :x: | :white_check_mark: runtime-query |
| Take screenshots | :x: | :white_check_mark: screenshot-capture |
| Full closed loop: Write → Test → Fix → Repeat | :x: | :white_check_mark: |
AI Playtest Loop
AI writes code → compiles → enters Play Mode → observes state → judges → fixes → repeats
↑ │
└─────────────────── fully automated loop ────────────────────────────────┘
The pattern: Act → Wait → Observe → Judge → Repeat
- Act:
runtime-invokecalls static methods to trigger game actions - Wait:
wait_playmode.py/wait_compile.pyhandle timing - Observe:
runtime-queryreads MonoBehaviour fields +screenshot-capturefor visuals - Judge: AI analyzes state/screenshots to decide PASS/FAIL
Auto-Playtest Example | AI Closed-Loop Guide | Playtest Tool Reference
Add Your Own Tools
Expose any static method to AI with a single attribute:
using UnityAiBridge;
[BridgeToolType]
public static partial class CustomTools
{
[BridgeTool("custom-greet")]
[System.ComponentModel.Description("Say hello")]
public static string Greet(string name = "World")
{
return $"Hello, {name}!";
}
}
The bridge discovers tools at Editor startup via reflection. No registration code, no config files. Parameters are automatically mapped to JSON Schema for the AI to call.
Security
Unity AI Bridge runs entirely on your local machine. The file IPC channel is scoped to your user's temp directory, and no network listeners are opened.
See SECURITY.md for details.
Compatibility
| Unity Version | Render Pipeline | Status |
|---|---|---|
| 2022.3 LTS+ | Built-in | Supported |
| 2022.3 LTS+ | URP | Supported |
| 2022.3 LTS+ | HDRP | Supported |
| 6000.x (Unity 6) | All | Supported |
Platforms: Windows, macOS
Contributing
Contributions are welcome! Please see CONTRIBUTING.md for guidelines.
- Report bugs and request features via GitHub Issues
- Submit pull requests against the
mainbranch - Add new tools by following the
[BridgeTool]pattern above
Acknowledgments
Unity AI Bridge is derived from Unity-MCP by Ivan Murzak (Apache License 2.0). See THIRD_PARTY_NOTICES.md for details.
License
Related MCP servers

io.github.buttonmonkey/mcp-loom
Stdio MCP proxy: intercepts oversized tool results into a queryable embedded DuckDB.

legacy2mcp
Turn a legacy SOAP/WSDL service into a safe, typed, schema-validated, audit-logged MCP server
Protocol- & auth-agnostic API connector: SOAP/REST behind any auth, config-driven. Lib/API/MCP.
SSH server management for AI agents with per-server read-only and allowlist security modes.

io.github.bx33661/wireshark-mcp
AI-powered packet analysis with tshark—security audits, threat detection, and network deep-dives in plain English.

