AI agents call get_memory to retrieve information from Engram without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns a single memory record from the SQLite database based on an ID parameter. It is a retrieval operation with no capability to modify, delete, or execute code. The verb 'recupera' (retrieves) and the context of fetching by ID confirm this is a read-only operation. Low severity because misuse would only expose stored data, not alter or destroy it.
From the tool's definition Tool name 'get_memory' and description 'Recupera una memoria específica por su ID' (Retrieves a specific memory by its ID) indicate a simple data retrieval operation with no side effects.
Attacks that exploit this kind of access
Recupera una memoria específica por su ID. It is categorised as a Read tool in the Engram MCP Server, which means it retrieves data without modifying state.
Register the Engram MCP server in PolicyLayer and add a rule for get_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.
get_memory is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_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 get_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.
get_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 →