Nox
- python
0
GitHub Stars
python
Language
4 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"rvforest-nox-mcp": {
"command": "nox-mcp",
"args": [],
"env": {
"YOUR_ENV": "<YOUR_ENV>"
}
}
}
}You can run nox automation tasks in your environment through a dedicated MCP server. This lets AI assistants discover and execute your nox sessions (like tests, linting, and builds) directly from your tooling, with structured outputs that are easy to parse.
How to use
You use the MCP server by configuring an MCP client in your AI-enabled workflow. Once connected, you can list available nox sessions and trigger them by name, tags, or keyword expressions. You can also override the Python version for a session when needed and receive JSON-formatted results that are easy for an assistant to interpret.
How to install
Prerequisites you need before starting:
-
Python 3.10+
-
nox installed and available in your PATH
Install the MCP server with one of the following methods
pip install nox-mcp
uv pip install nox-mcp
Configuration for MCP clients
Configure your MCP client to use the nox MCP server. You can point your client to either a direct command or to a wrapper that runs the MCP server via a launcher.
Claude Desktop example
{
"mcpServers": {
"nox": {
"command": "nox-mcp"
}
}
}
If you are using uvx to launch the MCP server, use this form
{
"mcpServers": {
"nox": {
"command": "uvx",
"args": ["nox-mcp"]
}
}
}
Available tools and how to use them
Once configured, you can call these tools to interact with your nox sessions. They provide a straightforward way to discover and run your automation tasks from an AI assistant.
Available tools
nox_list_sessions
List all available nox sessions in the current project with their names, Python versions, and descriptions.
nox_run_session
Run one or more nox sessions by names with optional filters for tags, keywords, and Python version overrides.