AI agents call memory_get 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.
The tool appears to retrieve persistent memory data from the Cortex vault. While the empty description reduces confidence slightly, the naming pattern 'memory_get' and context of other sibling read operations (memory_list, memory_recall) strongly suggest this is a data retrieval function with no side effects. No data creation, modification, deletion, or code execution is indicated.
From the tool's definition Tool name 'memory_get' suggests retrieval of stored memory data. No description provided, but naming convention and sibling tools (memory_list, memory_recall, memory_remind) that are clearly read-only retrieval operations indicate this is a query/fetch…
Documented attack patterns abuse exactly the kind of access memory_get 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_get:
{
"version": "1",
"default": "deny",
"tools": {
"memory_get": {}
}
}memory_get 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_get. 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_get: 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_get 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_get 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_get. 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_get 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.