AI agents call memory_remind to retrieve information from Cortex without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Although the tool description is empty (lowering confidence slightly), the semantic context strongly indicates this is a retrieval operation that accesses stored memories without creating, modifying, or deleting data. The function appears analogous to 'memory_recall' among sibling tools. No side effects or data mutations are implied.
From the tool's definition Tool name 'memory_remind' and server context indicating a persistent memory system for retrieving 'durable lessons' and 'surfacing relevant' information suggests retrieval operations.
Documented attack patterns abuse exactly the kind of access memory_remind gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Cortex, and nothing reaches the server without passing your rules. This is the rule we recommend for memory_remind:
{
"version": "1",
"default": "deny",
"tools": {
"memory_remind": {}
}
}memory_remind 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.
memory_remind. It is categorised as a Read tool in the Cortex MCP Server, which means it retrieves data without modifying state.
Register the Cortex MCP server in PolicyLayer and add a rule for memory_remind: 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 Cortex. Nothing to install.
memory_remind 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_remind 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_remind. 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_remind is provided by the Cortex MCP server (tt-wang/memem). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 14 Cortex tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
14 Cortex tools catalogued and risk-classified — across an index of 42,500+ MCP servers.