You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
* Update server instructions with new options
* Upgrade to a later version of Pydantic
This should have improved Python 3.14 support
* Swap order of instructions so Docker comes before local building
* Add fixed versions back to the README
* Update README to clarify the GitHub uvx command
**Required:** Install the [Unity MCP Plugin](https://github.com/CoplayDev/unity-mcp?tab=readme-ov-file#-step-1-install-the-unity-package) to connect Unity Editor with this MCP server.
14
+
**Required:** Install the [Unity MCP Plugin](https://github.com/CoplayDev/unity-mcp?tab=readme-ov-file#-step-1-install-the-unity-package) to connect Unity Editor with this MCP server. You also need `uvx` (requires [uv](https://docs.astral.sh/uv/)) to run the server.
Use this to run the latest released version from the repository. Change the version to `main` to run the latest unreleased changes from the repository.
docker run -p 8080:8080 msanatan/mcp-for-unity-server:latest --transport http --http-url http://0.0.0.0:8080
129
88
```
130
89
131
-
### Option 3: Using Docker
90
+
**Build Locally:**
132
91
133
92
```bash
134
93
docker build -t unity-mcp-server .
135
94
docker run -p 8080:8080 unity-mcp-server --transport http --http-url http://0.0.0.0:8080
136
95
```
137
96
138
-
Configure your MCP client with `"url": "http://localhost:8080/mcp"`. For stdio-in-docker (rare), run the container with `--transport stdio` and use the same `command`/`args` pattern as the uv examples, wrapping it in `docker run -i ...` if needed.
97
+
Configure your MCP client with `"url": "http://localhost:8080/mcp"`.
0 commit comments