AI agents call check_credential_exists 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 queries vault metadata. The tool does not retrieve plaintext credentials (per the server's design), does not modify any state, and does not execute external operations. It simply checks the existence of a credential record for a given site.
From the tool's definition The tool 'check_credential_exists' with description '[🔐 Site Authentication] Check whether a credential is stored for a given site' performs a query operation that retrieves metadata about credential existence without accessing, modifying, or executing…
Attacks that exploit this kind of access
[🔐 Site Authentication] Check whether a credential is stored for a given 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 check_credential_exists: 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.
check_credential_exists 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 check_credential_exists 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 check_credential_exists. 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.
check_credential_exists 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 →