Provides real-time observability and debugging capabilities for Kubernetes clusters, including access to pods, services, nodes, events, and deployments with built-in health monitoring and connectivity analysis tools.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Kubernetes MCP Server check pod status in the production namespace"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A production-ready Model Context Protocol (MCP) server for Kubernetes observability and debugging.
MCP Server: Standardized interface for Kubernetes cluster access
Real-time Data: Live access to pods, services, nodes, and events
Debugging Tools: Built-in tools for cluster health and issue analysis
Production Ready: Clean, tested code ready for production use
Related MCP server: mcp-kubernetics
Kubernetes cluster (local or remote)
kubectl configured and working
Python 3.11+
pip package manager
git clone https://github.com/vivekbala/mcp.git
cd mcppython3.11 -m pip install -r requirements.txtpython3.11 verify_setup.pyk8s://pods - All pods with status and details
k8s://services - Services with endpoints and connectivity info
k8s://nodes - Node health and capacity info
k8s://events - Recent cluster events for troubleshooting
k8s://deployments - Deployment status and replica info
cluster_health_check - Comprehensive health analysis
check_pod_status - Pod status and issue identification
analyze_service_connectivity - Service endpoint analysis
get_pod_logs - Log retrieval and analysis
python3.11 demo_script.pypython3.11 debug_demo.pypython3.11 mcp_server.py{
"mcpServers": {
"kubernetes-observability": {
"command": "python3.11",
"args": ["/path/to/mcp_server.py"],
"env": {
"KUBECONFIG": "/path/to/kubeconfig"
}
}
}
}Use the MCP client libraries
Build custom debugging interfaces
Integrate with existing monitoring tools
Feel free to submit issues, feature requests, or pull requests to improve this MCP server.
This project is open source and available under the MIT License.
Ready to debug Kubernetes like a pro? 🚀
Clone this repo and start debugging your cluster issues today!
This server cannot be deployed
The Google GKE MCP server is a managed Model Context Protocol server that provides AI applications with tools to manage Google Kubernetes Engine (GKE) clusters and Kubernetes resources. It exposes a structured, discoverable interface that allows AI agents to interact with GKE and Kubernetes APIs, enabling them to inspect cluster configurations, retrieve Kubernetes resource YAMLs, monitor operations like cluster upgrades, diagnose issues, and optimize costs—all without needing to parse text output or use complex kubectl commands.
MCP observability. Query live traffic, errors, duration, and alerts from your AI agent.
Hosted MCP catalog with 30 tenant-isolated browser, RAG, AI, mail and media tools.
MCP-native AI SRE: ask what's broken in production, get a reviewed GitHub fix PR.