AI agents call search_vault_tools 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 tool retrieves metadata about available tools within the psamvault system—a read-only discovery mechanism. It has no side effects, does not execute code or commands, does not modify credentials or data, and does not trigger external operations. It is purely informational, similar to a help or list command, making it a straightforward Read category risk.
From the tool's definition Tool name 'search_vault_tools' and description 'Discover available psamvault tools' indicate a discovery/listing operation with no data modification or external action. The verb 'discover' and context '[🛠 Entry & Orientation]' suggest informational querying.
Attacks that exploit this kind of access
[🛠 Entry & Orientation] Discover available psamvault tools. 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 search_vault_tools: 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.
search_vault_tools 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 search_vault_tools 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 search_vault_tools. 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.
search_vault_tools 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 →