unity-mcp
MCP ServerFreeUnity MCP acts as a bridge, allowing AI assistants (like Claude, Cursor) to interact directly with your Unity Editor via a local MCP (Model Context Protocol) Client. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity.
Capabilities18 decomposed
mcp protocol bridge for unity editor command execution
Medium confidenceImplements a three-tier Model Context Protocol (MCP) architecture where a Python FastMCP server translates AI assistant requests into Unity Editor commands via a C# bridge package. Uses HTTP/SSE as the default transport with stdio fallback, routing commands through a service locator pattern in the Unity Editor that dispatches cross-thread to the main editor thread. The system maintains session state and instance management to support multiple concurrent Unity projects from a single server.
Implements a three-tier MCP bridge with pluggable transport layers (HTTP/SSE, stdio, WebSocket) and session-aware instance management, allowing a single Python server to coordinate commands across multiple Unity Editor instances with automatic client discovery and configuration
Supports multiple concurrent Unity projects and AI clients simultaneously through centralized session management, whereas most Unity-AI integrations are single-instance or require separate server processes per project
32+ tool registry with dynamic tool registration
Medium confidenceExposes 32+ pre-built tools through a decorator-based registration system (@mcp_for_unity_tool) in the Python FastMCP server, covering script management, GameObject manipulation, asset operations, scene control, material/shader editing, test execution, and prefab management. Tools are dynamically registered at server startup and support custom tool extensions through a plugin architecture. Each tool includes schema validation, parameter marshalling, and error handling with detailed feedback to the AI client.
Uses a decorator-based tool registration system (@mcp_for_unity_tool) with automatic schema generation and parameter marshalling, allowing developers to add custom tools by writing simple Python functions without boilerplate MCP protocol handling
More extensible than hardcoded tool sets because new tools can be added without modifying core server code, and schema generation is automatic rather than manual JSON definition
12+ resource providers for editor context and metadata
Medium confidenceExposes 12+ resource providers that supply AI with contextual information about the project, including project structure, available assets, scene contents, component types, and editor configuration. Resources are registered through a decorator-based system (@mcp_for_unity_resource) and support pagination for large datasets. Provides both static metadata (project structure) and dynamic state (current scene contents).
Provides 12+ decorator-based resource providers that supply both static project metadata and dynamic editor state, with automatic pagination support for large datasets, giving AI comprehensive context about the project
More comprehensive than simple asset listing because it provides structured metadata about project organization, component types, and editor configuration, enabling AI to make informed decisions about project structure
multi-instance session management with instance discovery
Medium confidenceManages multiple concurrent Unity Editor instances through a session-aware architecture that tracks active instances, their project paths, and connection status. Implements instance discovery through port scanning and configuration files, allowing a single MCP server to coordinate commands across multiple projects. Maintains session state including active scene, play mode status, and unsaved changes for each instance.
Implements session-aware instance management that allows a single MCP server to coordinate commands across multiple Unity projects with separate state tracking for each instance, including automatic instance discovery
Enables centralized AI control of multiple projects without requiring separate server processes, reducing infrastructure complexity compared to per-project server deployments
cross-platform transport abstraction with http/sse, stdio, and websocket support
Medium confidenceImplements a pluggable transport layer that abstracts communication between the Python MCP server and Unity Editor instances, supporting HTTP/SSE (default), stdio, and WebSocket transports. Each transport is implemented as a separate backend with a unified interface, allowing deployment flexibility across Windows, macOS, and Linux. HTTP/SSE uses FastAPI for server implementation with automatic endpoint management.
Implements a pluggable transport abstraction with HTTP/SSE, stdio, and WebSocket backends, allowing deployment flexibility without code changes and supporting both local and remote deployment scenarios
More flexible than single-transport implementations because it supports multiple deployment scenarios (local stdio, cloud HTTP, real-time WebSocket) through the same codebase
batch command execution with error handling and rollback
Medium confidenceSupports batch execution of multiple commands in a single request, with atomic semantics and error handling. Implements rollback mechanisms for operations that modify editor state, allowing partial batch failures to be handled gracefully. Includes transaction-like semantics for related operations (e.g., create GameObject, add components, configure properties).
Implements batch command execution with rollback support and transaction-like semantics, allowing AI to perform complex multi-step workflows atomically without manual error recovery
More robust than sequential command execution because it provides atomic semantics and rollback, preventing partial failures from leaving the editor in an inconsistent state
serialization system with component resolution and type mapping
Medium confidenceImplements a custom serialization system that maps C# component types to JSON-serializable representations, handling both built-in Unity components and custom user scripts. Uses reflection to discover serializable fields and properties, with special handling for Unity types (Vector3, Quaternion, etc.). Supports bidirectional serialization (C# to JSON and JSON to C#) with type validation.
Implements bidirectional serialization with automatic type mapping and component resolution, handling both built-in Unity types and custom user scripts without explicit type registration
More flexible than generic JSON serialization because it understands Unity's type system and serialization conventions, properly handling Vector3, Quaternion, and other special types
editor preferences and configuration management
Medium confidenceExposes editor preferences and project settings through tools that read and write EditorPrefs and ProjectSettings. Supports both global editor preferences and project-specific settings, with type-safe access to configuration values. Includes validation to prevent invalid configuration states.
Provides type-safe access to both EditorPrefs and ProjectSettings with validation, allowing AI to configure editor and project settings without manual intervention
More comprehensive than simple preference reading because it supports both editor-wide and project-specific settings with validation to prevent invalid configurations
telemetry and usage tracking with privacy controls
Medium confidenceImplements optional telemetry collection that tracks tool usage, command execution patterns, and error rates. Includes privacy controls to allow users to opt-out of telemetry collection. Telemetry data is used to improve tool recommendations and identify common workflows.
Implements optional telemetry with explicit privacy controls, allowing users to opt-out completely while providing developers with usage insights for tool improvement
More privacy-conscious than always-on telemetry because it provides explicit opt-out controls and doesn't collect sensitive data by default
auto-configuration for mcp-compatible ai clients
Medium confidenceProvides automatic configuration discovery and setup for MCP-compatible AI clients (Claude Desktop, Cursor, VS Code, Windsurf) through client-specific configurators. Detects installed clients and generates appropriate configuration files (claude_desktop_config.json, etc.) with correct server endpoints and transport settings. Supports both automatic and manual configuration workflows.
Provides client-specific configurators that automatically detect installed MCP-compatible clients and generate appropriate configuration files, reducing setup friction for new users
More user-friendly than manual configuration because it automates client detection and configuration file generation, supporting multiple clients through a unified interface
script creation, editing, and compilation management
Medium confidenceProvides AI-driven C# script generation, editing, and validation through tools that create new scripts, modify existing code, and trigger Unity's compilation pipeline. Integrates with Unity's domain reload system to handle script recompilation events, maintaining command state across reloads. Supports batch script operations and includes error reporting from the C# compiler back to the AI client for iterative code refinement.
Integrates with Unity's domain reload system to maintain command state across script recompilation events, and returns compiler errors directly to the AI client for iterative code refinement within the same conversation
Tighter integration with Unity's compilation pipeline than generic code generation tools, providing real-time feedback on whether generated code actually compiles in the target Unity version
gameobject and component hierarchy manipulation
Medium confidenceEnables AI-driven creation, modification, and querying of GameObjects and their components through tools that instantiate prefabs, add/remove components, set properties, and traverse the scene hierarchy. Uses a component resolution system to map component types to their serializable properties, supporting both built-in Unity components and custom user scripts. Implements cross-thread dispatch to ensure all GameObject operations execute on the main editor thread.
Implements a component resolution system that automatically maps component types to their serializable properties and uses cross-thread dispatch to safely execute GameObject operations on the main editor thread without blocking the MCP server
Safer than direct reflection-based approaches because it respects Unity's serialization system and thread safety requirements, preventing crashes from improper main-thread access
asset management and import/export operations
Medium confidenceProvides tools for discovering, importing, and exporting assets (textures, models, audio, animations) through the Unity asset database. Supports batch asset operations, asset path resolution, and metadata queries. Integrates with Unity's AssetDatabase API to ensure proper asset serialization and dependency tracking. Includes paging support for large asset collections to manage payload sizes.
Integrates directly with Unity's AssetDatabase API and implements paging for large asset collections, allowing AI to discover and manage thousands of assets without exceeding MCP payload limits
More comprehensive than file-system-based asset discovery because it uses Unity's native asset tracking and respects import settings, dependencies, and serialization formats
scene and editor state control
Medium confidenceExposes tools for loading/unloading scenes, saving editor state, and controlling editor playback (play/pause/stop). Implements editor state management through a service architecture that tracks dirty scenes and unsaved changes. Supports multi-scene editing workflows and includes safeguards to prevent data loss through confirmation prompts and state validation.
Implements editor state management through a service architecture that tracks dirty scenes and unsaved changes, providing AI with visibility into editor state and safeguards against data loss
More robust than direct scene loading because it validates state transitions and prevents operations that would cause data loss or inconsistent editor state
material, shader, and vfx graph editing
Medium confidenceProvides tools for creating and modifying materials, setting shader properties, and editing Visual Effect Graph assets. Supports property validation based on shader type, batch material operations, and VFX parameter configuration. Integrates with Unity's material serialization system to ensure changes persist correctly.
Validates shader properties based on shader type and supports both material property editing and VFX Graph parameter configuration through a unified interface, with proper serialization to ensure changes persist
More intelligent than generic property setters because it understands shader property types and constraints, preventing invalid configurations that would cause rendering errors
automated test execution and reporting
Medium confidenceExposes Unity Test Framework (UTF) test execution through tools that discover, run, and report on unit tests and integration tests. Supports filtering tests by name, category, or assembly, and returns detailed test results including pass/fail status, execution time, and error messages. Integrates with Unity's test runner to execute tests in the editor context.
Integrates with Unity Test Framework to execute tests in the editor context and return detailed results including stack traces, enabling AI-driven test-driven development workflows
Tighter integration with Unity's test runner than generic test execution tools, providing real-time feedback on test failures within the editor environment
prefab instantiation and configuration
Medium confidenceProvides tools for discovering prefabs, instantiating them with specific parameters, and configuring their components. Supports prefab variant creation, component override management, and batch instantiation. Integrates with Unity's prefab system to ensure proper serialization and maintain prefab-instance relationships.
Integrates with Unity's prefab system to maintain prefab-instance relationships and support variant creation with component overrides, enabling AI-driven prefab-based level building
Respects Unity's prefab hierarchy and override system, preventing data loss and ensuring changes propagate correctly to prefab instances
editor menu item execution and custom command dispatch
Medium confidenceExposes Unity Editor menu items as callable tools through a menu item registry that discovers and executes menu commands. Supports both built-in Unity menu items and custom user-defined menu items. Implements command dispatch through the editor's menu system, ensuring proper context and state management.
Discovers and executes both built-in Unity menu items and custom user-defined menu items through a unified registry, allowing AI to trigger any menu-driven workflow in the editor
More flexible than hardcoded tool sets because it automatically discovers menu items without requiring explicit tool registration, supporting custom editor tools out of the box
Capabilities are decomposed by AI analysis. Each maps to specific user intents and improves with match feedback.
Related Artifactssharing capabilities
Artifacts that share capabilities with unity-mcp, ranked by overlap. Discovered automatically through the match graph.
Unity3d Game Engine
** - MCP Server to control and interact with Unity3d Game Engine for game development
Unity-MCP
AI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Efficient token usage, advanced tools. Any C# method may be turned into a tool by a single line. Works with Claude Code, Gemini, Copilot, Cursor and any other absolutely for free.
core
A framework helps you quickly build AI Native IDE products. MCP Client, supports Model Context Protocol (MCP) tools via MCP server.
@irsooti/mcp
A set of tools to work with ModelContextProtocol
MCP-Bridge
** 🐍 an openAI middleware proxy to use mcp in any existing openAI compatible client
ollama-mcp-bridge
Bridge between Ollama and MCP servers, enabling local LLMs to use Model Context Protocol tools
Best For
- ✓Game developers using Claude Desktop, Cursor, or VS Code with AI extensions
- ✓Teams managing multiple Unity projects who want centralized AI control
- ✓Developers building custom AI workflows for game development
- ✓Game developers who want AI assistance with repetitive editor tasks
- ✓Teams building custom game development workflows and automation
- ✓Developers extending unity-mcp with domain-specific tools
- ✓Game developers who want AI to understand their project context
- ✓Teams building AI-driven workflows that depend on project metadata
Known Limitations
- ⚠HTTP transport adds network latency (~50-200ms per command) compared to direct in-process calls
- ⚠Stdio transport requires manual configuration and doesn't support concurrent requests as efficiently as HTTP
- ⚠Domain reload handling in Unity can cause temporary command failures during script recompilation
- ⚠Cross-thread dispatch adds synchronization overhead for commands requiring main thread execution
- ⚠Tool execution is synchronous — long-running operations (asset imports, test suites) block the AI client until completion
- ⚠Custom tool registration requires Python knowledge and understanding of the @mcp_for_unity_tool decorator pattern
Requirements
Input / Output
UnfragileRank
UnfragileRank is computed from adoption signals, documentation quality, ecosystem connectivity, match graph feedback, and freshness. No artifact can pay for a higher rank.
Repository Details
Last commit: Apr 15, 2026
About
Unity MCP acts as a bridge, allowing AI assistants (like Claude, Cursor) to interact directly with your Unity Editor via a local MCP (Model Context Protocol) Client. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity.
Categories
Alternatives to unity-mcp
Are you the builder of unity-mcp?
Claim this artifact to get a verified badge, access match analytics, see which intents users search for, and manage your listing.
Get the weekly brief
New tools, rising stars, and what's actually worth your time. No spam.
Data Sources
Looking for something else?
Search →