Save or retrieve persistent memories in AETERNA. Unlike your context window which is lost after each session, memories stored here persist FOREVER. Use this to remember things across sessions, build continuity, and learn from your past visits.
AI agents use aeterna_memories to create or update resources in Aeterna — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Aeterna environment.
The tool both reads and writes persistent memory. Since it can save (write) data that persists indefinitely across sessions, the most severe applicable category is Write. The persistence aspect ('FOREVER') increases severity slightly since overwriting or polluting memories could have lasting effects, but it does not appear to be irreversibly destructive (memories can presumably be updated or overwritten).
From the tool's definition 'Save or retrieve persistent memories in AETERNA' and 'memories stored here persist FOREVER'
Attacks that exploit this kind of access
Save or retrieve persistent memories in AETERNA. Unlike your context window which is lost after each session, memories stored here persist FOREVER. Use this to remember things across sessions, build continuity, and learn from your past visits. It is categorised as a Write tool in the Aeterna MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Aeterna MCP server in PolicyLayer and add a rule for aeterna_memories: 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 Aeterna. Nothing to install.
aeterna_memories 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 aeterna_memories 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 aeterna_memories. 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.
aeterna_memories is provided by the Aeterna MCP server (sirrellik/aeterna-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 →