uMCP is a server implementation of the MCP protocol designed specifically for Unity, used to connect AI agents to Unity applications, with security and scalability.
2.5 points
5.4K

What is uMCP?

uMCP is a server implementation based on the MCP protocol, designed specifically for communication with AI agents in Unity. It uses the streaming HTTP protocol without relying on other language runtimes, making communication more efficient and lightweight.

How to use uMCP?

uMCP communicates directly with MCP clients through the streaming HTTP protocol. Users only need to install the uMCP package in the Unity project and configure an MCP client that supports streaming HTTP (such as VSCode Agent Mode) to start interacting.

Use Cases

uMCP is suitable for development environments that require connecting AI agents to Unity projects, such as game development, simulation systems, or AI training platforms. Its security and scalability make it an ideal choice.

Main Features

Security
uMCP does not allow AI to execute arbitrary code. All operations must be authorized to ensure the security and controllability of the system.
Scalability
Users can extend the functionality of uMCP by customizing commands and tools to adapt to different application scenarios.
Lightweight
uMCP does not rely on additional language runtimes and only uses the streaming HTTP protocol, making deployment and operation more efficient.
Advantages
No need to rely on other language runtimes, easy to deploy
Supports custom commands for easy expansion
Safe and reliable, preventing unauthorized operations
Limitations
Only supports the streaming HTTP protocol, with limited compatibility
Requires certain programming knowledge to extend functionality
Currently mainly used in the Unity environment, with limited generality

How to Use

Install the uMCP package
Open the Package Manager in the Unity editor and install the uMCP package from the Git URL.
Start the Unity project
After the installation is complete, run the Unity project, and the uMCP server will start automatically.
Configure the MCP client
Configure the address of uMCP in an MCP client that supports streaming HTTP (such as VSCode Agent Mode): http://localhost:7225/sse.

Usage Examples

AI agent controls character movement
Through uMCP, the AI agent can send instructions to move characters in Unity, thereby achieving automated behavior in the scene.
Get scene information
The AI agent can request specific information in the Unity scene, such as the position or status of objects.

Frequently Asked Questions

Does uMCP support non-Unity environments?
How to add custom commands?
What dependencies does uMCP require?

Related Resources

uMCP GitHub repository
The official repository for uMCP source code and example code
MCP protocol documentation
Detailed description and specification of the MCP protocol
VSCode Agent Mode configuration guide
How to configure Agent Mode in VSCode to connect to uMCP

Installation

Copy the following command to your Client for configuration
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
5.7K
4.5 points
M
Moltbrain
MoltBrain is a long-term memory layer plugin designed for OpenClaw, MoltBook, and Claude Code, capable of automatically learning and recalling project context, providing intelligent search, observation recording, analysis statistics, and persistent storage functions.
TypeScript
5.3K
4.5 points
B
Bm.md
A feature-rich Markdown typesetting tool that supports multiple style themes and platform adaptation, providing real-time editing preview, image export, and API integration capabilities
TypeScript
4.9K
5 points
S
Security Detections MCP
Security Detections MCP is a server based on the Model Context Protocol that allows LLMs to query a unified security detection rule database covering Sigma, Splunk ESCU, Elastic, and KQL formats. The latest version 3.0 is upgraded to an autonomous detection engineering platform that can automatically extract TTPs from threat intelligence, analyze coverage gaps, generate SIEM-native format detection rules, run tests, and verify. The project includes over 71 tools, 11 pre-built workflow prompts, and a knowledge graph system, supporting multiple SIEM platforms.
TypeScript
5.2K
4 points
P
Paperbanana
Python
6.3K
5 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
6.9K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
7.6K
5 points
A
Apify MCP Server
The Apify MCP Server is a tool based on the Model Context Protocol (MCP) that allows AI assistants to extract data from websites such as social media, search engines, and e-commerce through thousands of ready-to-use crawlers, scrapers, and automation tools (Apify Actors). It supports OAuth and Skyfire proxy payment and can be integrated into MCP clients such as Claude and VS Code through HTTPS endpoints or local stdio.
TypeScript
7.7K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
24.6K
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
20.5K
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
73.2K
4.3 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
35.5K
5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
32.3K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
64.6K
4.5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
22.1K
4.5 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
96.7K
4.7 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase