List stored secret names and metadata. Values are never returned.
AI agents call vault_list to retrieve information from Secret Vault MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information (secret names and metadata) without modifying, deleting, executing, or transferring funds. The design explicitly excludes returning secret values, which significantly reduces the blast radius. Misuse by an AI agent would result in enumeration of stored secrets' identities but not disclosure of their contents, making this a low-severity read operation.
From the tool's definition Tool description explicitly states 'List stored secret names and metadata. Values are never returned.' The verb 'list' combined with metadata-only retrieval indicates a read operation.
Attacks that exploit this kind of access
List stored secret names and metadata. Values are never returned. It is categorised as a Read tool in the Secret Vault MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Secret Vault MCP Server MCP server in PolicyLayer and add a rule for vault_list: 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 Secret Vault MCP Server. Nothing to install.
vault_list 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 vault_list 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 vault_list. 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.
vault_list is provided by the Secret Vault MCP Server MCP server (sam-ueckert/vault-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 →