Comprehensively analyzes cluster nodes, pods, and resources to evaluate health
AI agents call full-diagnosis to retrieve information from K8s Doctor MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes existing Kubernetes cluster state (nodes, pods, resources) to provide diagnostics. It gathers information and performs analysis without modifying, deleting, or executing any operations that would change cluster state or trigger external actions. Classification as Read is appropriate with low severity since the blast radius of misuse is limited to information disclosure.
From the tool's definition Tool name 'full-diagnosis' and description 'analyzes cluster nodes, pods, and resources to evaluate health' indicate diagnostic/observational operations only.
Attacks that exploit this kind of access
Comprehensively analyzes cluster nodes, pods, and resources to evaluate health. It is categorised as a Read tool in the K8s Doctor MCP MCP Server, which means it retrieves data without modifying state.
Register the K8s Doctor MCP server in PolicyLayer and add a rule for full-diagnosis: 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 Doctor MCP. Nothing to install.
full-diagnosis is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the full-diagnosis 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 full-diagnosis. 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.
full-diagnosis is provided by the K8s Doctor MCP server (ongjin/k8s-doctor-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 →