- MONITOR
- ANALYZE
- RECONCILE
- HUMAN
Short answer
How can I track third party service spend with my AI?
Your AI uses OpenCost to pull cost totals and time-series data from your Kubernetes clusters. You can then compare these numbers against external service bills to find discrepancies. You'll get a clear view of how cluster activity correlates with outside costs.
Cost visibility outcomes
Where your data lands
What you get when your AI analyzes your spend.
MONITOR
Real-time cost tracking
The AI pulls current totals from OpenCost. You get a clear view of what your cluster is costing you right now.
ANALYZE
Trend identification
By pulling time-series data, your AI identifies when costs spiked. This helps you spot unusual usage patterns in your services.
RECONCILE
External service matching
Compare your cluster costs with Datadog or MongoDB Atlas bills. Your AI highlights where external spend doesn't align with cluster activity.
HUMAN
Manual budget decisions
The AI identifies the gaps, but you decide how to adjust your cloud budget or service tiers based on its findings.
The workflow
What your AI does when the data arrives.
The AI acts as a bridge between your cluster metrics and your financial oversight.
Fetch totals
The AI pulls the current cost figures from your Kubernetes environment.
get_custom_cost_totalMap trends
It gathers historical cost data to build a timeline of your spending.
get_custom_cost_timeseriesCross-reference
The AI compares these cluster totals against the external service costs you provide in chat.
get_custom_cost_totalReport findings
It summarizes the relationship between your cluster usage and third party service spend.
get_custom_cost_timeseries
Try it
Copy these to start.
Use these prompts to begin your cost analysis.
Starting points
These are opening lines. Swap out the service names like Datadog or MongoDB Atlas for the ones you actually use.
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"
}
}
}What was my total Kubernetes spend for the last 30 days?
Show me the cost time-series for my cluster over the last week.
Compare my OpenCost totals with my $500 Datadog bill.
Did my cluster costs spike at the same time my MongoDB Atlas bill went up?
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect OpenCost once, then ask.
Just link the MCP to your client. Your credentials stay encrypted, and you can start asking questions immediately.
Connect OpenCost to your AIFAQ
How this task behaves
- 01
Can the AI change my cloud provider settings?
No. The AI can only read cost data from OpenCost. It cannot modify your cluster or your external service accounts.
- 02
Does the AI see my actual credit card info?
No. It only accesses the cost metrics provided by the OpenCost data.
- 03
Can it automatically pay my Datadog bill?
No. The AI is limited to reading and analyzing cost data. It has no capability to execute payments or change billing settings.
- 04
How does it know what my Datadog bill is?
The AI doesn't pull Datadog data directly. You provide the Datadog cost information in the chat, and it compares that to the OpenCost data it fetches.
- 05
Can I see a graph of my spending?
The AI can pull the time-series data needed to understand trends, which you can then use to visualize your spending.
More questions about OpenCost? The Connector page answers them. See everything the OpenCost Connector can do
Connect OpenCost to Claude, Cursor, ChatGPT & more
