KubernetesLab

What changes when you put Agent Router in front of your MCP servers?

Authorization down to call arguments really does work. It costs about 20ms per response and the default deployment tops out around 100 requests per second, and one iteration-count setting turns out to own that cost. Writing the condition the way the documentation shows leaves tools/list returning nothing, so an agent finds no tools at all: wrap the CEL in has().September 16, 2026 · 15 min · Hoon Jo

What changes when you connect agents over A2A?

What A2A gives you is a contract for progress and cancellation. What it costs is a larger response (seven times plain HTTP for the same job) and 1.2 to 2.1 ms more per call. The authentication the agent card declares is not enforced by the SDK’s default setup, so read declaration and enforcement separately.September 14, 2026 · 18 min · Hoon Jo

What changes when you put a gateway in front of MCP?

The gateway hop costs under 1 ms per tool call and never improves p99, and in return you get control and observation the server cannot do on its own. One argument-conditioned policy was accepted and still did not enforce what it said, so turn a policy on and then check it with real calls.September 7, 2026 · 16 min · Hoon Jo

How much CPU and memory does a CNI actually use?

A CNI is picked once and rarely revisited, and there is no organized data on what it consumes day to day. Measuring 5 CNIs in 14 configurations under identical conditions showed an 8x memory spread, an eBPF map share that kubectl top never sees, and a 70% kube-proxy memory saving from the nftables mode that had not been published as a number.August 4, 2026 · 7 min · Hoon Jo

Does switching CLAUDE.md to AGENTS.md slow Claude Code down?

The two AGENTS.md migration workarounds (import, symlink) were measured on Kubernetes incident-response tasks: no penalty in speed or context-load tokens; deltas moved with the symlink control, marking them as run variance.July 3, 2026 · 4 min · Hoon Jo