AI agents call get_username_for_site to retrieve information from Psamvault without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that retrieves non-sensitive authentication metadata (username only). The tool explicitly excludes password exposure, limiting information disclosure risk. No side effects, modifications, or destructive actions are possible. The low blast radius and informational nature place this firmly in the Read category with low severity.
From the tool's definition Tool returns only the username for a site, explicitly stated as 'not the password'. The description indicates retrieval of stored metadata without access to sensitive secrets or ability to modify data.
Attacks that exploit this kind of access
[🔐 Site Authentication] Return the username (not the password) stored for a site. It is categorised as a Read tool in the Psamvault MCP Server, which means it retrieves data without modifying state.
Register the Psamvault MCP server in PolicyLayer and add a rule for get_username_for_site: 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 Psamvault. Nothing to install.
get_username_for_site 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_username_for_site 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_username_for_site. 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_username_for_site is provided by the Psamvault MCP server (psam-717/psamvault-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 →