Skip to main content
Glama
fleet-intelligence-mcp-server

fleet-intelligence-mcp-server

Fleet Intelligence MCP Server

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.

Quick start

npm install
cp config.example.yaml config.yaml
npm run build
npm start

Server runs at http://127.0.0.1:3000/mcp (change host / port in config).

Related MCP server: databricks-genie-MCP

Config (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://127.0.0.1:9094

ACM hub

source: kubernetes
url: ~/.kube/config

Leave url empty for default kubeconfig or in-cluster config.

Global Hub

source: globalhub
url: postgres://readonly:password@host:5432/dbname

Get the postgres URL:

oc get secret multicluster-global-hub-storage \
  -n multicluster-global-hub \
  -o jsonpath='{.data.database_uri_with_readonlyuser}' | base64 -d

Connect Cursor

{
  "mcpServers": {
    "fleet-intelligence": {
      "url": "http://127.0.0.1:3000/mcp"
    }
  }
}

MCP tools

Tool

What it returns

list_clusters

All clusters with registration health

list_active_alerts

Firing alerts from Alertmanager

list_nodes

Nodes with Ready status, conditions, CPU/memory

cluster_observability

Full picture: nodes + metrics + alerts

fleet_health

Total / healthy / warning / critical / unknown counts

list_unhealthy_clusters

Unhealthy clusters with reasons

cluster_health

Registration health for one cluster

explain_cluster_health

Full condition data for LLM summarization

Prometheus port-forward (required for metrics)

kubectl port-forward -n openshift-monitoring svc/thanos-querier 9091:9091
kubectl port-forward -n openshift-monitoring svc/alertmanager-main 9094:9094

Then set observability.prometheusUrl and alertmanagerUrl in config.yaml.

Example prompts: example_prompts.md

License

Apache-2.0

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      Exposes Kubernetes cluster state with specialized telecom awareness of 5G Core network functions and topologies to MCP-compatible LLMs. It enables natural language analysis of 5G workloads, network slices, UPF data planes, and cluster health.
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      Connects to the Databricks Genie API, enabling LLMs to ask natural language questions, run SQL queries, and interact with Databricks conversational agents.
      17
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables management of Red Hat OpenShift clusters through the OpenShift Cluster Manager API, allowing users to interact with cluster resources using natural language.
      8
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      MCP server that connects LLMs to Kubernetes clusters for troubleshooting, scanning failing pods, diagnosing root causes, and applying guarded fixes or generating manifests via natural language.
      32 PyPI
      MIT