AI agents call cja_list_metrics to retrieve information from Adobe Cja without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to retrieve or enumerate available metrics in Adobe Customer Journey Analytics for use in analytics queries. This is a Read operation with minimal blast radius—an AI agent calling this tool can only discover what metrics exist, not modify or delete anything. The low severity reflects that metric enumeration poses no risk to data integrity or security.
From the tool's definition Tool name 'cja_list_metrics' indicates a list/retrieval operation. The 'list' verb is a read-only action that queries and returns data without modification.
Attacks that exploit this kind of access
cja_list_metrics. It is categorised as a Read tool in the Adobe Cja MCP Server, which means it retrieves data without modifying state.
Register the Adobe Cja MCP server in PolicyLayer and add a rule for cja_list_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 Adobe Cja. Nothing to install.
cja_list_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 cja_list_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 cja_list_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.
cja_list_metrics is provided by the Adobe Cja MCP server (markhilton/adobe-cja-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 →