Retrieve a specific observation by its ID.
AI agents call memory_get to retrieve information from Mono Memory MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
memory_get performs a simple lookup/retrieval operation against a SQLite-backed memory store. There is no modification, deletion, code execution, or financial impact. The operation is read-only and returns existing data identified by ID. Severity is low because even if an agent retrieves sensitive stored context, the tool itself causes no harm and the data is already stored in the system's own database.
From the tool's definition Tool description explicitly states 'Retrieve a specific observation by its ID' — retrieves data with no side effects.
Attacks that exploit this kind of access
Retrieve a specific observation by its ID. It is categorised as a Read tool in the Mono Memory MCP MCP Server, which means it retrieves data without modifying state.
Register the Mono Memory MCP server in PolicyLayer and add a rule for memory_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 Mono Memory MCP. Nothing to install.
memory_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 memory_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 memory_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.
memory_get is provided by the Mono Memory MCP server (potato-castle/mono-memory-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 →