AI agents invoke switch_context to trigger actions in Cert Manager. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Switching the Kubernetes context changes which cluster all subsequent operations target. This is an external operation with broad side effects — it redirects every future command (including destructive ones) to a potentially different cluster. It is not a simple read, write, or delete of data, but rather a reconfiguration of the active execution environment, making Execute the most appropriate category.
From the tool's definition Switch kubeconfig context
Documented attack patterns abuse exactly the kind of access switch_context gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Cert Manager, and nothing reaches the server without passing your rules. This is the rule we recommend for switch_context:
{
"version": "1",
"default": "deny",
"tools": {
"switch_context": {
"limits": [
{
"counter": "switch_context_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}switch_context stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Switch kubeconfig context. It is categorised as a Execute tool in the Cert Manager MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Cert Manager MCP server in PolicyLayer and add a rule for switch_context: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Cert Manager. Nothing to install.
switch_context is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the switch_context rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for switch_context. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
switch_context is provided by the Cert Manager MCP server (pibblokto/cert-manager-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Cert Manager, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 Cert Manager tools catalogued and risk-classified — across an index of 43,000+ MCP servers.