Save a session summary before ending. Call at the end of each conversation.
AI agents use end_session to create or update resources in Claude Memory — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Memory environment.
This tool saves session summaries to persistent storage in Supabase, which is a data creation/modification operation. It is categorized as Write rather than Destructive because the action is reversible (summaries can be updated or deleted later), and it poses minimal risk even if misused.
From the tool's definition The tool 'Save a session summary before ending' performs a write operation by storing session data in Supabase. The description indicates it creates or modifies data (session summaries) but is reversible and non-destructive.
Documented attack patterns abuse exactly the kind of access end_session gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Memory, and nothing reaches the server without passing your rules. This is the rule we recommend for end_session:
{
"version": "1",
"default": "deny",
"tools": {
"end_session": {
"limits": [
{
"counter": "end_session_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}end_session stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Save a session summary before ending. Call at the end of each conversation. It is categorised as a Write tool in the Claude Memory MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Claude Memory MCP server in PolicyLayer and add a rule for end_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 Claude Memory. Nothing to install.
end_session 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 end_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 end_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.
end_session is provided by the Claude Memory MCP server (jordanl61/claude-memory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claude Memory, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
7 Claude Memory tools catalogued and risk-classified — across an index of 43,000+ MCP servers.