- METRICS
- INVENTORY
- ANALYSIS
- HUMAN
Short answer
How can I check my cluster's CPU and memory usage via chat?
Your AI uses Flystack tools to fetch real-time resource data for specific clusters. You get immediate visibility into CPU and memory consumption through natural language queries. This breakdown shows you how to set it up.
Monitoring outcomes.
Real-time visibility outcomes.
What you get when your AI talks to Flystack.
METRICS
Live resource snapshots
The AI pulls current CPU and memory stats for any cluster you name. You get the numbers you need to spot spikes instantly.
INVENTORY
Cluster list access
Your agent identifies all active clusters in your Flystack account. This makes it easy to target specific environments for inspection.
ANALYSIS
Automated trend spotting
Your AI interprets the raw metrics to tell you if a cluster is hitting its limits. It turns raw data into clear status updates.
HUMAN
Manual intervention
The AI identifies the problem, but you still handle the actual scaling or restarts. It provides the evidence you need to make those calls.
The workflow
What your AI does when you ask for metrics.
The AI handles the data fetching so you can focus on the diagnosis.
Identify clusters
The AI first looks up your available Flystack infrastructure to find the right targets.
list_flystack_clustersFetch resource data
Once the cluster is identified, the AI pulls the specific CPU and memory numbers.
get_cluster_metricsSummarize status
The AI translates the raw metric values into a readable summary of current performance.
get_cluster_metricsReport findings
The agent presents the final resource usage report directly in your chat interface.
get_cluster_metrics
Try it
Copy these to start.
Use these prompts to begin monitoring your infrastructure.
Starting points
Replace the cluster names with your actual Flystack cluster identifiers.
Flystack Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_if3hKQNHyk1KZFSZ1tlM4V31U1AyDcvmjO34ifLn/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Flystack capabilities are ready to use.
{
"mcpServers": {
"flystack-mcp": {
"url": "https://edge.vinkius.com/vk_preview_if3hKQNHyk1KZFSZ1tlM4V31U1AyDcvmjO34ifLn/mcp"
}
}
}List all my Flystack clusters.
What is the current CPU usage for the production-cluster?
Check the memory usage for the staging-cluster.
Which clusters are showing high CPU usage right now?
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect Flystack once, then ask.
One connection gives your AI access to your Flystack metrics. Your credentials stay encrypted and secure on our end.
Connect Flystack to your AIFAQ
How the monitoring works
- 01
Can my AI restart a cluster if it sees high CPU?
No. This MCP only provides read access to metrics. You must perform any scaling or restart actions manually in Flystack.
- 02
How often does the AI get updated metrics?
The AI fetches fresh data from Flystack every time you ask a question, ensuring you see real-time usage.
- 03
Can the AI delete a cluster through chat?
No. The tools provided are strictly for listing clusters and retrieving metrics. There are no tools for deleting or modifying infrastructure.
- 04
Do I need to give my AI my Flystack password?
No. You connect via Vinkius, which manages the connection securely. Your AI client never sees your raw login credentials.
- 05
Can I see network latency metrics?
No. This specific connector is limited to CPU and memory usage metrics.
More questions about Flystack? See everything the Flystack Connector can do
Connect Flystack to Claude, Cursor, ChatGPT & more
