fleet-intelligence-mcp-server
Connects an LLM to your fleet of clusters via ACM or Multicluster Global Hub, enabling queries about fleet health, unhealthy clusters, and detailed cluster conditions.
README
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).
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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.