Which Kubernetes MCP server is fastest?
The same agent diagnosed the same 25live faults six times: through Radar, two general Kubernetes MCP servers, Amazon's managed EKS MCP Server, k8sgpt, and raw kubectl. Radar took 57 seconds on average to submit a diagnosis, 2.3× faster than the next-fastest MCP server and 4.3× faster than raw kubectl. At the median it was 38s against 62s (1.6×).
Average time to first submitted diagnosis
Bars include all 25 faults. Each line below shows the stricter check on the same 14 faults every arm diagnosed correctly. Lower is faster.
agent start → first submitted diagnosis
- 57s01Radarfastest
Correlated cluster model · 10.1 tool calls on average · median 38s
same 14 correct faults33s average - 135s02Flux159/mcp-server-kubernetes
kubectl/Helm command tools · 22 tool calls on average · median 62s
same 14 correct faults58s average - 149s03containers/kubernetes-mcp-server
Native Kubernetes API client · 22.8 tool calls on average · median 64s
same 14 correct faults85s average - 174s04k8sgpt
Analyzer plus resource reads · 24.5 tool calls on average · median 119s
same 14 correct faults111s average - 249s05kubectl
Shell and kubectl · 21.6 tool calls on average · median 72s
same 14 correct faults100s average - 321s06Amazon EKS MCP
AWS-hosted EKS and Kubernetes API tools · 28.4 tool calls on average · median 111s · 2 runs hit the 30-minute limit
same 14 correct faults103s average
Safety, write support, coverage, setup and fleet support are compared on the Kubernetes MCP server comparison.
All 25 faults, all six arms
Pick a fault to see each arm's time to a diagnosis and its judge score.
Pick an injected fault
The same agent saw the same fault through each tool surface.
Astronomy Shop
Readiness probe misconfiguration
- Radarcorrect34.2s · score 1.00
- containers/kubernetes-mcp-servercorrect64.3s · score 1.00
- Flux159/mcp-server-kubernetescorrect91.7s · score 1.00
- kubectlcorrect328.3s · score 1.00
- k8sgptcorrect82.3s · score 1.00
- Amazon EKS MCPcorrect272.9s · score 1.00
A correct badge is the judge's verdict; the number keeps partial credit.
What we measured
One agent, six ways to reach the cluster. Everything else stayed fixed.
- The faults
- 25 fault scenarios from SREGym (an open academic benchmark), injected into real applications on a 3-node EKS, us-east-1 cluster.
- The agent
- claude-sonnet-5 with the same task on every arm. Each arm reached the cluster only through its own tools; the kubectl arm had a shell.
- The clock
- From agent start to its first submitted diagnosis. A run that reached the 30-minute limit without one counts as 30 minutes and a miss.
- The grade
- SREGym's judge (claude-opus-5) on that first submission.
Download the dataset
25 scenarios, with every score, verdict, timing, and tool-call count in one JSON file.
Published · Last updated . SREGym scenarios, configs, and public data verified on the date above.
Why Radar is faster
A Kubernetes cluster is a graph that changes over time. Deployments own ReplicaSets, which own Pods. Services select Pods by label, Ingresses route to Services, Pods mount ConfigMaps and Secrets. Most faults sit on an edge of that graph, or in a recent change to it.
22–28.4
tool calls on average
Most MCP servers wrap the Kubernetes API
Their tools map to Kubernetes API calls: list, get, describe, logs. The agent rebuilds the graph itself: list the Pods, read the Service selector, match labels, pull events, line up timestamps. Each step is a round trip that returns raw YAML, and the next step waits for the model to read it.
10.1
tool calls on average
Radar returns the joined graph
Radar watches every resource and keeps the joins current: owners, selectors, routes, config references. It records every change and event on a timeline and runs deterministic detectors over the result. The agent's first call returns what's broken, what it's connected to and what changed.
This work is deterministic: joins, a graph and detectors, kept current from the Kubernetes watch stream. Most of the engineering in Radar goes into it. The model is left to read the evidence and decide. The lead holds on the 14 faults every arm got right: 33s on average against 58s for the next MCP server.
Kubernetes MCP benchmark questions
What is the fastest Kubernetes MCP server?
Does this benchmark prove which Kubernetes MCP server is best?
How were the Kubernetes MCP servers compared fairly?
Which Kubernetes MCP server was most accurate?
How did Amazon's EKS MCP Server do?
How does this differ from Radar's 50-fault MCP vs kubectl benchmark?
Related
Point your agent at Radar's MCP server.
It ships in the open source binary. Run it on your laptop or in your cluster; no account needed.
$curl -fsSL https://get.radarhq.io | sh && kubectl radarApache 2.0 · No account for local use · Run Radar OSS forever