Save structured memories directly. The AI extracts and classifies knowledge itself, then passes it here for safety checks and persistence. Accepts a single {content, type} or batch {items: [...]}. This is the primary tool for saving project knowledge — no server-side LLM needed.
AI agents use remember to create or update resources in OpenMemBrain — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your OpenMemBrain environment.
The tool writes data to a knowledge base but includes safety checks and is reversible (memories can be rejected or managed via sibling tools like reject_all_candidates). The presence of approval workflows and the ability to list/audit memories indicates this is a controlled write operation rather than destructive.
From the tool's definition Tool description explicitly states 'Save structured memories directly' and 'passes it here for safety checks and persistence.' It creates or modifies persistent data (memories/knowledge base) reversibly.
Attacks that exploit this kind of access
Save structured memories directly. The AI extracts and classifies knowledge itself, then passes it here for safety checks and persistence. Accepts a single {content, type} or batch {items: [...]}. This is the primary tool for saving project knowledge — no server-side LLM needed. It is categorised as a Write tool in the OpenMemBrain MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the OpenMemBrain 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 OpenMemBrain. 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 OpenMemBrain MCP server (mohamadalhusseinie/openmembrain). 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 →