Read a specific GCE metadata path (auto-redacts secret-bearing responses).
AI agents call describe_metadata 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 performs a GET-like operation on GCE metadata endpoints. Although it retrieves potentially sensitive information (metadata can include instance details, service account information, and other sensitive configuration), the operation is non-destructive and read-only. The auto-redaction of secret-bearing responses partially mitigates exposure risk.
From the tool's definition Tool name 'describe_metadata' and description 'Read a specific GCE metadata path (auto-redacts secret-bearing responses)' indicate a read-only operation that retrieves metadata without modification or deletion.
Attacks that exploit this kind of access
Read a specific GCE metadata path (auto-redacts secret-bearing responses). 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 describe_metadata: 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.
describe_metadata 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 describe_metadata 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 describe_metadata. 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.
describe_metadata 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 →