Full audit report (credentials, RBAC, namespace, findings).
AI agents call get_report to retrieve information from Gke Cred Audit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and presents audit findings and inventory data (credentials, RBAC rules, namespace configuration) without altering any state. It is fundamentally a read operation that queries and aggregates information.
From the tool's definition Tool name 'get_report' and description 'Full audit report (credentials, RBAC, namespace, findings)' indicate retrieval and aggregation of existing audit data with no modification or deletion of resources.
Attacks that exploit this kind of access
Full audit report (credentials, RBAC, namespace, findings). It is categorised as a Read tool in the Gke Cred Audit MCP Server, which means it retrieves data without modifying state.
Register the Gke Cred Audit MCP server in PolicyLayer and add a rule for get_report: 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 Gke Cred Audit. Nothing to install.
get_report 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 get_report 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 get_report. 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.
get_report is provided by the Gke Cred Audit MCP server (rrupesh/mcp-test). 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 →