What makes uMCP different from other MCP implementations?
uMCP communicates directly with the MCP client via Streamable HTTP, eliminating the need for Python, Node.js, or other language runtimes for a more efficient and lightweight setup.
@mika-f
Basic information
uMCP is a server implementation of the MCP protocol, designed for working with the AI in Unity.
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
uMCP is a minimalistic and efficient MCP protocol server implementation for connecting AI agents to Unity applications. It communicates directly with MCP clients using the Streamable HTTP protocol without additional language runtimes, making it lightweight and Unity‑native.
Install the CoreFramework package in Unity (2022.3 LTS or newer) via OpenUPM or Git URL. The MCP server starts automatically when the Unity project runs. Then configure your MCP client (e.g., VSCode Agent Mode, Cursor, CLINE) to point to http://localhost:7225/sse or http://localhost:7225/mcp.
McpServerToolType and McpServerTool attributes.uMCP communicates directly with the MCP client via Streamable HTTP, eliminating the need for Python, Node.js, or other language runtimes for a more efficient and lightweight setup.
Unity Editor version 2022.3 LTS or newer. The MCP client must support Streamable HTTP (e.g., VSCode Agent Mode, Cursor, CLINE).
Create a class with the `[McpServerToolType]` attribute and add static methods marked with `[McpServerTool]` and `[Description]`. Return an `IToolResult` such as `TextResult`. See the provided example in the README.
It uses Streamable HTTP, accessible at endpoints `/sse` and `/mcp` on the default port `7225`.
Yes, it is designed as a Unity Package and runs inside the Unity Editor. It does not support standalone builds.

Model Context Protocol Servers
Open-source MCP to use Blender with any LLM
Painless E2E Automation for Mobile and Web

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
Comments