AI agents call memory_search 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.
A search function across persistent memory entries is a query/retrieval operation with no side effects. Even if misconfigured or exploited, the tool cannot modify, delete, or execute external operations—it only retrieves stored data. The blast radius is minimal: worst case, an AI agent retrieves unintended memory entries, which poses no operational risk beyond information disclosure within the same vault system.
From the tool's definition Tool name 'memory_search' with sibling tools including 'memory_get', 'memory_list', and 'memory_recall' indicates a retrieval operation. The server description emphasizes storage and surfacing of memories without mentioning modification capabilities.
Documented attack patterns abuse exactly the kind of access memory_search 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_search:
{
"version": "1",
"default": "deny",
"tools": {
"memory_search": {}
}
} memory_search 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_search. 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_search: 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_search 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_search 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_search. 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_search 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.