Get a MNEMOS memory by id (mem_XXX).
AI agents call mnemos.memory_get to retrieve information from Mnemos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves stored memory data by identifier. The verb 'Get' and the absence of any modification language ('create', 'update', 'delete') confirm it is a Read operation. The blast radius is minimal—an agent retrieving its own memory poses no security risk to data integrity or external systems. Severity is low.
From the tool's definition Tool name 'memory_get' and description 'Get a MNEMOS memory by id' indicate a retrieval operation with no modification or side effects.
Documented attack patterns abuse exactly the kind of access mnemos.memory_get gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mnemos, and nothing reaches the server without passing your rules. This is the rule we recommend for mnemos.memory_get:
{
"version": "1",
"default": "deny",
"tools": {
"mnemos.memory_get": {}
}
}mnemos.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.
Get a MNEMOS memory by id (mem_XXX). It is categorised as a Read tool in the Mnemos MCP Server, which means it retrieves data without modifying state.
Register the Mnemos MCP server in PolicyLayer and add a rule for mnemos.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 Mnemos. Nothing to install.
mnemos.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 mnemos.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 mnemos.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.
mnemos.memory_get is provided by the Mnemos MCP server (ncz-os/mnemos). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mnemos, 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.
15 Mnemos tools catalogued and risk-classified — across an index of 43,000+ MCP servers.