Retrieve relevant memories using semantic search.
AI agents call query_memory to retrieve information from CyberMem without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs data retrieval via semantic search over stored memories. It has no capability to create, modify, delete, or execute operations—it only fetches information. The blast radius of misuse is minimal; an agent querying memory cannot cause harm beyond potentially accessing sensitive cached context, which is mitigated by the memory system's design. Classified as Read with low severity.
From the tool's definition Tool name 'query_memory' and description 'Retrieve relevant memories using semantic search' indicate a read-only operation that queries existing data without modification or side effects.
Documented attack patterns abuse exactly the kind of access query_memory gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and CyberMem, and nothing reaches the server without passing your rules. This is the rule we recommend for query_memory:
{
"version": "1",
"default": "deny",
"tools": {
"query_memory": {}
}
}query_memory 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.
Retrieve relevant memories using semantic search. It is categorised as a Read tool in the CyberMem MCP Server, which means it retrieves data without modifying state.
Register the CyberMem MCP server in PolicyLayer and add a rule for query_memory: 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 CyberMem. Nothing to install.
query_memory 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 query_memory 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 query_memory. 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.
query_memory is provided by the CyberMem MCP server (mikhailkogan17/cybermem). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from CyberMem, 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.
5 CyberMem tools catalogued and risk-classified — across an index of 43,000+ MCP servers.