AI agents use save_memories 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.
This tool creates or modifies data in a SQLite database by persisting multiple memory records in a single transaction. It is reversible (data can be deleted, modified, or updated later), making it a Write operation rather than Destructive.
From the tool's definition Tool name 'save_memories' and description 'Guarda múltiples memorias en una sola transacción SQLite' (saves multiple memories in a single SQLite transaction).
Attacks that exploit this kind of access
Guarda múltiples memorias en una sola transacción SQLite. Ideal para bootstrapping de contexto masivo o guardar varias notas de golpe. Más eficiente que llamar save_memory repetidamente. 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 save_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 Engram. Nothing to install.
save_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 save_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 save_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.
save_memories 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 →