About Kubeledger
Kubeledger is an MCP server in the Science category: system of Record for Kubernetes cost accounting: per-namespace CPU, memory and GPU usage, with the 30% non-allocatable overhead made visible. Connects to AI assistants via MCP (Claude, Gemini, Mistral, Cursor) for plain-language analysis. Formerly Kube-Opex-Analytics.
Install
git clone https://github.com/realopslabs/kubeledgerThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (10)
compare_periods14-day aggregate vs. monthly trajectory + trend direction
Parameters not published.
describe_datasetCapabilities: metrics, scales, cost model, freshness
Parameters not published.
get_efficiencyAggregated `usage / requests` ratio per namespace
Parameters not published.
get_efficiency_timeseriesHourly efficiency factor (`rf`) series
Parameters not published.
get_namespace_breakdownProportional breakdown + concentration + cluster overhead
Parameters not published.
get_timeseriesHourly usage series over the last 7 days
Parameters not published.
get_top_consumersRanking by usage on a given date
Parameters not published.
get_usageUsage time series per namespace for a (metric, scale)
Parameters not published.
group_namespacesAggregate namespaces matching a glob pattern
Parameters not published.
list_namespacesDiscovered namespaces, classified application / system / special
Parameters not published.
Ask AI
Ask AI about Kubeledger
Powered by Claude · Grounded in docs
Security checks
6 checks have not been run yet.