Allows monitoring and managing a fleet of Kubernetes clusters, including health checks, listing unhealthy clusters, and explaining cluster health conditions.
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., "@fleet-intelligence-mcp-server Which clusters are unhealthy?"
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.
MCP server for ACM / Multicluster Global Hub. Connect an LLM to your fleet and ask things like:
How healthy is my fleet?
Which clusters are unhealthy?
Why is cluster-east unhealthy?
Everything is configured in one file: config.yaml.
npm install
cp config.example.yaml config.yaml
npm run build
npm startServer runs at http://127.0.0.1:3000/mcp (change host / port in config).
Related MCP server: databricks-genie-MCP
config.yaml)# Data source: kubernetes (ACM hub) or globalhub (Postgres)
source: kubernetes
url: ~/.kube/config
# MCP HTTP server
host: 127.0.0.1
port: 3000
name: fleet-intelligence-mcp-server
# Prometheus / Alertmanager — port-forward first (see config.example.yaml)
observability:
prometheusUrl: http://127.0.0.1:9091
alertmanagerUrl: http://127.0.0.1:9094source: kubernetes
url: ~/.kube/configLeave url empty for default kubeconfig or in-cluster config.
source: globalhub
url: postgres://readonly:password@host:5432/dbnameGet the postgres URL:
oc get secret multicluster-global-hub-storage \
-n multicluster-global-hub \
-o jsonpath='{.data.database_uri_with_readonlyuser}' | base64 -d{
"mcpServers": {
"fleet-intelligence": {
"url": "http://127.0.0.1:3000/mcp"
}
}
}Tool | What it returns |
| All clusters with registration health |
| Firing alerts from Alertmanager |
| Nodes with Ready status, conditions, CPU/memory |
| Full picture: nodes + metrics + alerts |
| Total / healthy / warning / critical / unknown counts |
| Unhealthy clusters with reasons |
| Registration health for one cluster |
| Full condition data for LLM summarization |
kubectl port-forward -n openshift-monitoring svc/thanos-querier 9091:9091
kubectl port-forward -n openshift-monitoring svc/alertmanager-main 9094:9094Then set observability.prometheusUrl and alertmanagerUrl in config.yaml.
Example prompts: example_prompts.md
Apache-2.0
This server cannot be deployed
Connects AI assistants to CloudQuell multi-cloud and AI cost, savings, anomaly, and budget data.
MCP-Native LLM Orchestration Agent
Build and supervise fleets of agents from Claude Code, Codex or Cursor. Connects over OAuth.
Connect LLM tools to your Algolia account with user-scoped access for internal workflows.
