AI agents call cja_validate_calculated_metric 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.
Validation tools generally read/check data against rules without modifying anything. The 'validate' prefix strongly implies a read-only check operation. However, the description is empty, which reduces confidence. Based on the sibling tools context (Adobe CJA analytics), this likely validates a calculated metric definition before creation. Severity is low as validation typically has minimal blast radius.
From the tool's definition Tool name 'cja_validate_calculated_metric' suggests validation, which is typically a read/check operation with no side effects.
Attacks that exploit this kind of access
cja_validate_calculated_metric. 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_validate_calculated_metric: 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_validate_calculated_metric 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_validate_calculated_metric 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_validate_calculated_metric. 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_validate_calculated_metric 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 →