AI agents call search_all_unique_properties to retrieve information from Pen without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries property values from a node tree structure without any side effects or data modification. It is purely informational, similar to a database query or search operation. The search operation has minimal blast radius even if misused by an agent, as it only exposes existing data values rather than enabling changes to the system state.
From the tool's definition Tool description states it 'Recursively search for all unique property values on the node tree' - uses search/query terminology with no modification, creation, or deletion of data mentioned.
Attacks that exploit this kind of access
Recursively search for all unique property values on the node tree under provided parent IDs. It is categorised as a Read tool in the Pen MCP Server, which means it retrieves data without modifying state.
Register the Pen MCP server in PolicyLayer and add a rule for search_all_unique_properties: 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 Pen. Nothing to install.
search_all_unique_properties 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_all_unique_properties 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_all_unique_properties. 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_all_unique_properties is provided by the Pen MCP server (@zseven-w/pen-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 →