AI agents call list_secrets to retrieve information from Secr without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about secrets (key names only, not sensitive values) without side effects. While it reads from a sensitive secrets management system, the absence of values and read-only nature places it in the Read category. Severity is medium rather than low because exposure of secret key names could inform an attacker about secrets management structure, even without the actual secret values.
From the tool's definition Tool name is 'list_secrets' and description states it lists 'secret key names (no values)' - a read-only retrieval operation with no modification capability.
Attacks that exploit this kind of access
List secret key names (no values) with optional search. It is categorised as a Read tool in the Secr MCP Server, which means it retrieves data without modifying state.
Register the Secr MCP server in PolicyLayer and add a rule for list_secrets: 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 Secr. Nothing to install.
list_secrets 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 list_secrets 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 list_secrets. 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.
list_secrets is provided by the Secr MCP server (secr-dev/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 →