Return recent memories, newest first.
AI agents call memory_recent to retrieve information from Codemem without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns stored memory data in chronological order. It performs no write, delete, execute, or financial operations—only retrieval. The action is passive information access, making it a Read category tool with low severity since misuse would only expose previously stored context data without enabling destructive or operational changes.
From the tool's definition Tool name 'memory_recent' and description 'Return recent memories, newest first' indicate a retrieval operation with no modification or side effects.
Documented attack patterns abuse exactly the kind of access memory_recent gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Codemem, and nothing reaches the server without passing your rules. This is the rule we recommend for memory_recent:
{
"version": "1",
"default": "deny",
"tools": {
"memory_recent": {}
}
}memory_recent 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.
Return recent memories, newest first. It is categorised as a Read tool in the Codemem MCP Server, which means it retrieves data without modifying state.
Register the Codemem MCP server in PolicyLayer and add a rule for memory_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 Codemem. Nothing to install.
memory_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 memory_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 memory_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.
memory_recent is provided by the Codemem MCP server (kunickiaj/codemem). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Codemem, 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.
13 Codemem tools catalogued and risk-classified — across an index of 43,000+ MCP servers.