AI agents invoke switch_context to trigger actions in kube-MCP. 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 Kubernetes context changes the active cluster/namespace target for all subsequent operations. This is not a simple read or write — it triggers an operational state change that affects which cluster all future commands are executed against. Misuse could cause an AI agent to inadvertently target a production cluster instead of a dev cluster, leading to high-blast-radius consequences.
From the tool's definition Switch Kubernetes context
Attacks that exploit this kind of access
Switch Kubernetes context. It is categorised as a Execute tool in the kube-MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the kube- 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 kube-MCP. 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 kube- MCP server (siddjoshi/kube-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →