AI agents call appd_query_metrics 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 metric data from AppDynamics without creating, modifying, deleting, or executing any operations. It is a query operation that reads historical metrics within a specified time window. No data modification, code execution, or irreversible actions are possible. The read-only nature of the server confirms this classification.
From the tool's definition Tool description states 'Fetch one or more metric paths over a time range' and the server is explicitly described as 'read-only MCP server'.
Attacks that exploit this kind of access
Fetch one or more metric paths over a time range using metric-data-v2. Defaults to BEFORE_NOW 30 minutes with rollup=true. Surfaces granularity and long-window warnings. 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_query_metrics: 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_query_metrics 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_query_metrics 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_query_metrics. 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_query_metrics 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 →