diagnose_pod

diagnose_pod

Server K8s jingyanjiang/k8s-mcp
Category Read
Risk class Low
Parameters 00 required

What diagnose_pod does on K8s

AI agents call diagnose_pod to retrieve information from K8s without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why diagnose_pod needs a policy

The name 'diagnose_pod' implies reading and analyzing pod status, logs, or events — a read/inspect operation with no apparent side effects. However, the empty description lowers confidence. Given the sibling tools context (exec_command, describe_resource, get_configmap), diagnosis tools typically aggregate read-only information.

From the tool's definition Tool name 'diagnose_pod' suggests inspection/querying of pod state; description is empty and uninformative.

Questions about diagnose_pod

What does the diagnose_pod tool do? +

diagnose_pod. It is categorised as a Read tool in the K8s MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on diagnose_pod? +

Register the K8s MCP server in PolicyLayer and add a rule for diagnose_pod: 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 K8s. Nothing to install.

What risk level is diagnose_pod? +

diagnose_pod is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit diagnose_pod? +

Yes. Add a rate_limit block to the diagnose_pod 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.

How do I block diagnose_pod completely? +

Set action: deny in the PolicyLayer policy for diagnose_pod. 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.

What MCP server provides diagnose_pod? +

diagnose_pod is provided by the K8s MCP server (jingyanjiang/k8s-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.