mkp

MKP is a Model Context Protocol (MCP) server designed specifically for Kubernetes environments. It enables developers to manage and interact with model contexts effectively, facilitating seamless communication between various microservices. By using MKP, you can streamline your workflows and enhance the integration of machine learning models into your Kubernetes applications.

Once connected to the MKP server, you can interact with it using standard HTTP requests. You can send queries to fetch model context details, update configurations, or manage context lifecycles. The server is optimized for handling JSON payloads, so structure your queries accordingly to ensure efficient data retrieval and manipulation.

Prerequisites

Before you install MKP, ensure you have the following prerequisites:

• A running Kubernetes cluster.
• kubectl installed and configured to interact with your cluster.
• Node.js (if applicable) for running JavaScript-based commands.

Option A: Quick Start with npx

If you want to quickly start using MKP, you can run the following command:

npx -y @StacklokLabs/mkp

Option B: Global Install Alternative

For a global installation, use the following command:

npm install -g @StacklokLabs/mkp

When configuring MKP, ensure you set the appropriate environment variables for your Kubernetes cluster, such as KUBE_CONFIG to point to your kubeconfig file. Be aware that network policies in your cluster may affect connectivity, so verify that the MKP server has the necessary permissions to access model context resources.