- ANALYSIS
- USAGE
- AUDIT
- HUMAN
Short answer
How can I match my K8s usage to my cloud bill?
Your AI pulls resource allocation data from OpenCost and compares it to the actual costs reported by your cloud provider. This identifies where your cluster usage and invoices diverge. You'll see exactly where the money is going.
The outcomes.
Where the data lands.
The AI processes the raw numbers into these specific outcomes.
ANALYSIS
Discrepancy reports
The AI compares cluster metrics against provider invoices. You get a clear view of any missing or unexpected costs.
USAGE
Resource mapping
The AI maps specific Kubernetes workloads to their actual dollar cost. This shows which pods or namespaces are driving your bill.
AUDIT
Billing verification
The AI validates that your cloud provider is charging you correctly for the resources your cluster actually used.
HUMAN
Manual adjustments
The AI flags anomalies that require you to manually investigate or adjust your cloud provider's billing settings.
The workflow
What your AI does when the data arrives.
The AI handles the heavy lifting of data comparison so you don't have to manually export CSVs.
Fetch cluster usage
The AI pulls the current resource allocation data from your Kubernetes cluster.
get_allocationFetch cloud costs
The AI retrieves the actual billing data from your cloud provider to see what you were charged.
get_cloud_costIdentify gaps
The AI compares the two datasets to find mismatches between what the cluster used and what the provider billed.
get_allocationget_cloud_costSummarize findings
The AI presents the delta between usage and billing in a format you can act on immediately.
get_cloud_cost
Try it
Copy these to start.
Use these prompts to begin your reconciliation.
Starting points
Replace the specific cluster or provider names with your own details.
OpenCost Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_5JgTTx4dCCg1vy5LoQY7EOXCEeiHxNr943mMQtmk/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 — OpenCost capabilities are ready to use.
{
"mcpServers": {
"opencost-k8s-cost-mcp": {
"url": "https://edge.vinkius.com/vk_preview_5JgTTx4dCCg1vy5LoQY7EOXCEeiHxNr943mMQtmk/mcp"
}
}
}Compare my Kubernetes resource allocation in the production cluster with my AWS bill.
Find the discrepancy between my OpenCost usage data and my Google Cloud invoice.
Which namespaces in my cluster are responsible for the highest cloud costs this month?
Check if my Azure billing matches the resource usage reported by OpenCost.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect OpenCost once, then ask.
One connection gives your AI access to your cluster metrics. Your credentials stay encrypted and secure on our side.
Connect OpenCost to your AIFAQ
How this task behaves.
- 01
Can the AI change my cloud billing settings?
No. The AI can only read usage and cost data. It cannot modify your cloud provider's billing configurations or your Kubernetes settings.
- 02
Does the AI delete any cluster data?
No. The AI only performs read operations to fetch data for comparison. It has no capability to delete or modify your cluster resources.
- 03
How does it handle different cloud providers?
The AI uses the cloud cost tool to pull data from the specific provider you specify in your prompt.
- 04
Can I use this to automate my monthly billing reports?
Yes. You can ask your AI to generate a summary of the differences between usage and billing for any given period.
- 05
What happens if the cloud bill and cluster usage don't match?
The AI will highlight the specific delta and identify which resources or namespaces are causing the mismatch.
More questions about OpenCost? The Connector page answers them. See everything the OpenCost Connector can do
Connect OpenCost to Claude, Cursor, ChatGPT & more
