$ loading_
Get Kubernetes deployment insights, metrics, history, and pre-release risk assessments.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "mcp-deploy-intel" yet — see the docs or source repo.
Review the latest deployment of payment-service in the production cluster, summarize workload status, key Prometheus metrics, recent change history, and generate a risk brief on whether it is safe to release.
A pre-release risk brief with service health, abnormal metrics, change summary, and a release recommendation.
List all workloads in the checkout namespace and provide a detailed snapshot for checkout-api, including replica status, recent deployment history, and related monitoring metrics to help diagnose post-release issues.
A workload inventory and service snapshot highlighting unhealthy replicas, suspicious deployment timing, and key metric changes.
Query the past 14 days of deployment history and core performance metric trends for recommendation-service, then compile a concise report explaining which changes may have caused latency increases.
A report correlating deployment history with metric trends, highlighting high-risk changes and their likely impact.
Filter Kubernetes warning events so AI can diagnose cluster issues faster.
Inspect Kubernetes clusters via MCP by listing pods, namespaces, nodes, and events.
Let AI manage Kubernetes clusters and Helm for deployment and troubleshooting.
Safely access Kubernetes clusters via MCP with read-only, permission-aware operations.
Manage Kubernetes clusters, resources, backups, and diagnostics using natural language.
Use AI to generate and optimize Docker and Kubernetes containerization workflows.