AI agents use restore_memory to create or update resources in Engram — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Engram environment.
The tool restores/reverts data to a previous state, which is a reversible modification operation. It does not create new data (Write, not Create), nor does it permanently delete (not Destructive). While it changes state, the operation is reversible by restoring again.
From the tool's definition Tool description states it 'Restaura una memoria a un estado anterior' (restores a memory to a prior state stored in its history). This modifies existing data by reverting it to a previous version.
Attacks that exploit this kind of access
Restaura una memoria a un estado anterior almacenado en su historial. It is categorised as a Write tool in the Engram MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Engram MCP server in PolicyLayer and add a rule for restore_memory: 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 Engram. Nothing to install.
restore_memory 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 restore_memory 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 restore_memory. 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.
restore_memory is provided by the Engram MCP server (jacksini/engram-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 →