AI agents call show_api_key_status to retrieve information from Z Zero without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a passive check on API key configuration and displays only a prefix for debugging purposes. No side effects, data modification, code execution, or financial transactions occur. It is purely informational, fitting the Read category with low severity since the information disclosed (key prefix only) is limited and intended for debugging.
From the tool's definition Tool name 'show_api_key_status' and description 'Check if Passport Key is configured. Shows prefix only, for debugging.' indicate a read-only diagnostic operation that retrieves configuration status without modifying, executing, or transferring funds.
Attacks that exploit this kind of access
Check if Passport Key is configured. Shows prefix only, for debugging. It is categorised as a Read tool in the Z Zero MCP Server, which means it retrieves data without modifying state.
Register the Z Zero MCP server in PolicyLayer and add a rule for show_api_key_status: 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 Z Zero. Nothing to install.
show_api_key_status 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 show_api_key_status 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 show_api_key_status. 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.
show_api_key_status is provided by the Z Zero MCP server (z-zero-mcp-server). 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 →