AI agents call entity_get to retrieve information from Mementos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries entity data (details, relations summary, memory count) with no side effects or modifications. It is a pure read operation that fits the Read category definition: 'retrieves or queries data; no side effects (search, list, get, fetch)'. The low severity reflects minimal blast radius if misused by an AI agent - it can only leak information about entities already in the system.
From the tool's definition Tool description states 'Get entity details by name or ID, including relations summary and memory count' - uses 'Get' and retrieves information without modifying data.
Attacks that exploit this kind of access
Get entity details by name or ID, including relations summary and memory count. It is categorised as a Read tool in the Mementos MCP Server, which means it retrieves data without modifying state.
Register the Mementos MCP server in PolicyLayer and add a rule for entity_get: 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 Mementos. Nothing to install.
entity_get 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 entity_get 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 entity_get. 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.
entity_get is provided by the Mementos MCP server (@hasna/mementos). 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 →