Approve, reject, or remove a published memory. Requires moderator permissions (can_moderate). Actions: - approve: Mark a pending memory as approved (visible in default searches) - reject: Reject a pending memory (hidden from default searches) - remove: Remove a previously approved memory (hidden ...
AI agents use remember_moderate to create or update resources in Remember — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Remember environment.
The tool modifies the visibility/status of memories (approve, reject, remove from searches). While 'remove' hides a memory, the description says it is 'hidden from default searches' rather than permanently deleted, suggesting reversibility. This makes Write the most appropriate category.
From the tool's definition Approve, reject, or remove a published memory. Actions: approve, reject, remove — hidden from default searches
Attacks that exploit this kind of access
Approve, reject, or remove a published memory. Requires moderator permissions (can_moderate). Actions: - approve: Mark a pending memory as approved (visible in default searches) - reject: Reject a pending memory (hidden from default searches) - remove: Remove a previously approved memory (hidden from default searches) Must specify either space_id or group_id to identify where the memory is published. It is categorised as a Write tool in the Remember MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Remember MCP server in PolicyLayer and add a rule for remember_moderate: 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 Remember. Nothing to install.
remember_moderate 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_moderate 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_moderate. 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_moderate is provided by the Remember MCP server (@prmichaelsen/remember-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 →