AI agents call appd_get_metric_hierarchy to retrieve information from Appd without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries metric hierarchy data from AppDynamics without side effects. It navigates a tree structure and returns results—a pure read operation. The caching behavior and lack of any write/execute/destructive operations confirm it poses minimal risk.
From the tool's definition Tool name begins with 'get_', described as 'Walk the metric hierarchy' and 'returns' data. The server is explicitly described as 'read-only' and no modification, deletion, or execution capabilities are mentioned.
Attacks that exploit this kind of access
Walk the metric hierarchy for one application. Without metricPath returns top-level folders; with metricPath returns the children at that level. Cached for 5 minutes. It is categorised as a Read tool in the Appd MCP Server, which means it retrieves data without modifying state.
Register the Appd MCP server in PolicyLayer and add a rule for appd_get_metric_hierarchy: 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 Appd. Nothing to install.
appd_get_metric_hierarchy 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 appd_get_metric_hierarchy 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 appd_get_metric_hierarchy. 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.
appd_get_metric_hierarchy is provided by the Appd MCP server (jagalliers/appd-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 →