Create a new memory. Use for milestones, decisions, and notable facts.
AI agents use memory_remember to create or update resources in Codemem — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Codemem environment.
This tool creates new memory entries in a persistent storage system. Creation of data is a Write operation. The severity is low because memories in a coding session context are informational artifacts that can be deleted or modified (as evidenced by sibling tools like 'memory_forget'), making this reversible and low-blast-radius even if an agent creates spurious or incorrect memories.
From the tool's definition Tool name 'memory_remember' combined with description 'Create a new memory' explicitly indicates creation of new data. The description lists use cases (milestones, decisions, notable facts) that are reversible record-keeping operations.
Documented attack patterns abuse exactly the kind of access memory_remember 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_remember:
{
"version": "1",
"default": "deny",
"tools": {
"memory_remember": {
"limits": [
{
"counter": "memory_remember_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}memory_remember stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Create a new memory. Use for milestones, decisions, and notable facts. It is categorised as a Write tool in the Codemem MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Codemem MCP server in PolicyLayer and add a rule for memory_remember: 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_remember is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the memory_remember 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_remember. 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_remember 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.