37 tools. 12 can modify or destroy data without limits.
3 destructive tools with no built-in limits. Policy required.
Last updated:
Destructive tools (helm_uninstall, pods_delete, resources_delete) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.
Write operations (helm_install, kiali_manage_istio_config, kiali_manage_istio_config_read) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.
Execute tools (pods_exec, pods_run, resources_scale) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.
Intercept sits between your agent and Kubernetes. Every tool call checked against your policy before it executes — so your agent can do its job without breaking things.
npx -y @policylayer/intercept scan -- npx -y @kubernetes-mcp-server helm_uninstall:
rules:
- action: deny Destructive tools should never be available to autonomous agents without human approval.
helm_install:
rules:
- rate_limit: 30/hour Prevents bulk unintended modifications from agents caught in loops.
configuration_contexts_list:
rules:
- rate_limit: 60/minute Controls API costs and prevents retry loops from exhausting upstream rate limits.
Yes. The Kubernetes server exposes 3 destructive tools including helm_uninstall, pods_delete, resources_delete. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.
The Kubernetes server has 5 write tools including helm_install, kiali_manage_istio_config, kiali_manage_istio_config_read. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.
37 tools across 4 categories: Destructive, Execute, Read, Write. 25 are read-only. 12 can modify, create, or delete data.
One line change. Instead of running the Kubernetes server directly, prefix it with Intercept: intercept -c io-github-containers-kubernetes-mcp-server.yaml -- npx -y @kubernetes-mcp-server. Download a pre-built policy from policylayer.com/policies/io-github-containers-kubernetes-mcp-server and adjust the limits to match your use case.
Starter policies available for each. Same risk classification, same one-command setup.
Set budgets, approvals, and hard limits across MCP servers.
npx -y @policylayer/intercept init