AI agents call memory_get to retrieve information from Codemem without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves a single memory item by its identifier. It has no side effects—it only reads and returns data from the persistent memory store. This is a straightforward Read operation with minimal security risk, as it cannot modify, delete, or execute any external operations. The severity is low because fetching stored context data poses no blast radius threat even if misused by an agent.
From the tool's definition Tool name 'memory_get' and description 'Fetch a single memory item by ID' indicate retrieval of stored data without modification or deletion.
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 Codemem, 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.
Fetch a single memory item by ID. It is categorised as a Read tool in the Codemem MCP Server, which means it retrieves data without modifying state.
Register the Codemem 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 Codemem. 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 Codemem MCP server (kunickiaj/codemem). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Codemem, 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.
13 Codemem tools catalogued and risk-classified — across an index of 43,000+ MCP servers.