Leverages Model Context Protocol to integrate AI-driven coding automation with Kubernetes management, enabling seamless interaction between Codename Goose AI agent and Minikube clusters for efficient software development and deployment.
Unlock the full potential of kube-mcp through LangDB's AI Gateway. Get enterprise-grade security, analytics, and seamless integration with zero configuration.
Free tier available • No credit card required
Goto https://aistudio.google.com/ and get yourself an API Key. Currently, gemini-2.0-pro-exp-02-05 LLM is available absolutely free of charge. Other models available for very cheap price also.
Goose is an open source AI agent that supercharges your software development by automating coding tasks. We will use Codename Goose as it has a built in MCP client. Install Codename Goose by following the steps here https://block.github.io/goose/docs/getting-started/installation. Setup GOOGLE_API_KEY environment variable so that Goose knows to use Gemini API. Understand how to configure using goose configure
and start as session using goose session
.
Read about MCP by reading the documentation : https://modelcontextprotocol.io/introduction and specifically the Python SDK : https://github.com/modelcontextprotocol/python-sdk
Clone this repository and test it using mcp dev server.py
. Note that this project uses uv
package manager instead of pip. Learn about uv
by reading docs : https://github.com/astral-sh/uv
This project uses the kubernetes python client: https://github.com/kubernetes-client/python
Install minikube by following isntructions : https://minikube.sigs.k8s.io/docs/start/?arch=%2Flinux%2Fx86-64%2Fstable%2Fbinary+download
Ensure that the config to the cluster is provided to the MCP server. Look at the KubernetesManager
and config.load_kube_config()
to understand how the config is loaded.
Add the MCP Server as an extension by reading the following docs : https://block.github.io/goose/docs/getting-started/using-extensions
Start a new goose session using command goose session --with-builtin developer --with-extension "uvx kube-mcp"
Try giving a command in Goose and make it interact with Minikube using the MCP Server
Discover shared experiences
Shared threads will appear here, showcasing real-world applications and insights from the community. Check back soon for updates!