AI agents use remember to create or update resources in Memmd — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Memmd environment.
This is a Write operation because it creates and modifies data (memory entries) in a shared knowledge base. Severity is medium because while the tool itself is reversible (memory can be edited or cleared via sibling tools like 'forget'), misuse by an AI agent could inject false information, contradictory data, or manipulated context into shared memory used across multiple AI clients, potentially affecting downstream…
From the tool's definition Tool name 'remember' and description states 'Add memory content' — this creates or modifies data (memory entries) in a shared state across multiple AI clients.
Attacks that exploit this kind of access
Add memory content with automatic dedupe/contradiction merge. It is categorised as a Write tool in the Memmd MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Memmd MCP server in PolicyLayer and add a rule for 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 Memmd. Nothing to install.
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 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 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.
remember is provided by the Memmd MCP server (matamong/memmd-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →