AI agents call argocd_app_diff to retrieve information from Kube Lint without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
argocd_app_diff performs a comparison query of ArgoCD application states. It does not create, modify, delete, or execute any changes; it only retrieves and presents differences for inspection. This is a pure information-retrieval operation with no side effects, fitting the Read category.
From the tool's definition Tool description states 'Show diff between live and desired state' — this is a read-only comparison operation that retrieves and displays information without modifying any state.
Attacks that exploit this kind of access
Show diff between live and desired state of an ArgoCD application.\n. It is categorised as a Read tool in the Kube Lint MCP Server, which means it retrieves data without modifying state.
Register the Kube Lint MCP server in PolicyLayer and add a rule for argocd_app_diff: 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 Lint. Nothing to install.
argocd_app_diff 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 argocd_app_diff 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 argocd_app_diff. 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.
argocd_app_diff is provided by the Kube Lint MCP server (sophotechlabs/kube-lint-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 →