memory_session_end
AI agents use memory_session_end to create or update resources in Eve Memory — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Eve Memory environment.
With an empty description, classification relies on the tool name and context. 'memory_session_end' likely finalizes or closes a memory session, which may involve writing/committing session data to persistent memory. Given sibling tools like memory_ingest and memory_forget, ending a session could trigger write operations (saving session state) or potentially destructive cleanup.
From the tool's definition Tool name 'memory_session_end' and empty description. Sibling tools include memory_ingest, memory_forget, memory_search, suggesting a memory management service.
Attacks that exploit this kind of access
memory_session_end. It is categorised as a Write tool in the Eve Memory MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Eve Memory MCP server in PolicyLayer and add a rule for memory_session_end: 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 Eve Memory. Nothing to install.
memory_session_end 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 memory_session_end 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_session_end. 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_session_end is provided by the Eve Memory MCP server (sherifkozman/eve-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 →