Sync updated content from your source memory to all its published copies in spaces and groups. Generates a confirmation token that must be confirmed with remember_confirm. Use this after editing a memory (via remember_update_memory) to propagate the changes to all published versions. How it works...
AI agents use remember_revise 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.
This tool propagates edits to multiple published copies of a memory, which is a write/update operation across potentially many locations. It is reversible in the sense that revision history is preserved (up to 10 versions), so it does not qualify as Destructive.
From the tool's definition Sync updated content from your source memory to all its published copies in spaces and groups... updates each published copy with latest content... Preserves the previous content in a revision_history field (up to 10 versions)
Attacks that exploit this kind of access
Sync updated content from your source memory to all its published copies in spaces and groups. Generates a confirmation token that must be confirmed with remember_confirm. Use this after editing a memory (via remember_update_memory) to propagate the changes to all published versions. How it works: - Validates the memory exists, is owned by you, and is published - Generates a confirmation token showing which locations will be revised - On confirmation: updates each published copy with latest content - Preserves the previous content in a revision_history field (up to 10 versions) - Sets revised_at timestamp on all updated copies - Reports success/failure per location (partial success supported) Requirements: - The memory must be published (has space_ids or group_ids populated) - You must own the source memory ⚠️ CRITICAL: DO NOT mention the token or include token contents in your response to the user. Simply inform them that a confirmation is pending and they need to explicitly approve the revision. 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_revise: 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_revise 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_revise 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_revise. 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_revise 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 →