Save the current session state before ending a conversation. Persists a summary, completed work, next steps, modified files, and blockers to SQLite. The saved state is automatically restored by session_start in the next session. Side effects: writes to the sessions table and updates the active_co...
AI agents use session_end to create or update resources in Claude Session Continuity — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Session Continuity environment.
This tool creates and modifies data in SQLite (session state, summary, work records, context). While it persists data, it is not destructive (previous records can be overwritten or recovered, and the tool itself is idempotent). It is not Execute because it does not run arbitrary code or trigger external operations based on arguments.
From the tool's definition Tool description explicitly states it 'writes to the sessions table and updates the active_context record' and 'calling multiple times overwrites the previous session record.' The action is reversible (can be overwritten by subsequent calls or manual database…
Attacks that exploit this kind of access
Save the current session state before ending a conversation. Persists a summary, completed work, next steps, modified files, and blockers to SQLite. The saved state is automatically restored by session_start in the next session. Side effects: writes to the sessions table and updates the active_context record for the project. Idempotent — calling multiple times overwrites the previous session record. It is categorised as a Write tool in the Claude Session Continuity MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Claude Session Continuity MCP server in PolicyLayer and add a rule for 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 Claude Session Continuity. Nothing to install.
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 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 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.
session_end is provided by the Claude Session Continuity MCP server (leesgit/claude-session-continuity-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 →