AI agents call list_recent_memories to retrieve information from ContextKeep without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical data (recently updated memories) in a read-only manner. There is no capability to modify, delete, execute code, or affect financial systems. The blast radius of misuse is minimal—an agent could only view existing stored memories, which poses no destructive risk.
From the tool's definition Tool name 'list_recent_memories' and description 'List the 10 most recently updated memories' indicate a retrieval operation with no side effects. It queries and returns existing memory data without modifying, deleting, or executing any actions.
Documented attack patterns abuse exactly the kind of access list_recent_memories gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ContextKeep, and nothing reaches the server without passing your rules. This is the rule we recommend for list_recent_memories:
{
"version": "1",
"default": "deny",
"tools": {
"list_recent_memories": {}
}
}list_recent_memories is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
List the 10 most recently updated memories. It is categorised as a Read tool in the ContextKeep MCP Server, which means it retrieves data without modifying state.
Register the ContextKeep MCP server in PolicyLayer and add a rule for list_recent_memories: 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 ContextKeep. Nothing to install.
list_recent_memories 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_memories 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_memories. 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_memories is provided by the ContextKeep MCP server (mordang7/contextkeep). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ContextKeep, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 ContextKeep tools catalogued and risk-classified — across an index of 43,000+ MCP servers.