AI agents call vault_list to retrieve information from Vault MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
vault_list retrieves metadata about stored credentials (site IDs and types) without exposing or modifying any sensitive data. It has no side effects and presents minimal risk—even if an agent misuses it, the attacker learns only organizational structure, not actual credentials. This is a standard read operation.
From the tool's definition Tool description states it 'List[s] all available credentials' and 'Returns only site IDs and types — no secrets.' The explicit exclusion of secret values and retrieval-only nature confirm this is a non-destructive query operation.
Attacks that exploit this kind of access
List all available credentials in the vault. Returns only site IDs and types — no secrets. It is categorised as a Read tool in the Vault MCP MCP Server, which means it retrieves data without modifying state.
Register the Vault 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 Vault MCP. 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 Vault MCP server (zerocreds-com/zerocreds-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 →