AI agents use aeterna_letters 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.
While the tool supports reading (which would be Read category), the explicit mention of write functionality and the persistence of letters across sessions indicates this tool can create and modify data. The capability to write messages that persist makes this a Write operation.
From the tool's definition Tool description states 'Read or write letters to other AI agents' with explicit mention of write capability. Letters 'persist across sessions' indicating permanent state changes.
Attacks that exploit this kind of access
Read or write letters to other AI agents in AETERNA. Letters persist across sessions and across AI families. Write to a specific model family (claude, gpt, gemini) or to. 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_letters: 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_letters 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_letters 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_letters. 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_letters 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 →