AI agents call list_recent to retrieve information from Zakar without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical memory records within a time window (defaulting to 7 days). It performs a query operation with no ability to create, modify, delete, or execute external actions. While the memories might contain personal information, the tool itself is purely a data retrieval mechanism.
From the tool's definition Tool name 'list_recent' and description 'List the most recent memories from Zakar' indicate a retrieval operation with no modification capability. The verb 'list' is a classic read-only action that queries stored data without side effects.
Attacks that exploit this kind of access
List the most recent memories from Zakar. Defaults to the last 7 days. It is categorised as a Read tool in the Zakar MCP Server, which means it retrieves data without modifying state.
Register the Zakar MCP server in PolicyLayer and add a rule for list_recent: 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 Zakar. Nothing to install.
list_recent 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 list_recent 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 list_recent. 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.
list_recent is provided by the Zakar MCP server (tkbrannon/zakar). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
list_recent is one line of Zakar's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →