get_session
AI agents call get_session to retrieve information from Memory MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to retrieve session information from the persistent memory store. Without a description, confidence is moderately reduced, but the naming pattern ('get_' prefix) and the fact that it coexists with write ('save_memory') and delete ('delete_memory') operations strongly suggests this is a read-only retrieval function.
From the tool's definition Tool named 'get_session' with empty description, part of a Memory MCP server that provides 'searchable access to conversation history'. The name and server context indicate retrieval of session data.
Attacks that exploit this kind of access
get_session. It is categorised as a Read tool in the Memory MCP MCP Server, which means it retrieves data without modifying state.
Register the Memory MCP server in PolicyLayer and add a rule for get_session: 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 Memory MCP. Nothing to install.
get_session 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_session 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_session. 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_session is provided by the Memory MCP server (nerdyaustin/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 →