Sync session state before context compaction (called via PreCompactHook).
AI agents use pre_compact_sync to create or update resources in Session Buddy — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Session Buddy environment.
This tool writes/persists session state data to storage before a compaction event. It is a Write operation (saving/updating state), not destructive since it preserves data rather than deleting it. Severity is medium because misuse could corrupt session state or cause data inconsistencies, but it doesn't delete or execute arbitrary code.
From the tool's definition 'Sync session state before context compaction' — performs a state synchronization (write) operation prior to compaction
Attacks that exploit this kind of access
Sync session state before context compaction (called via PreCompactHook). It is categorised as a Write tool in the Session Buddy MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Session Buddy MCP server in PolicyLayer and add a rule for pre_compact_sync: 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 Session Buddy. Nothing to install.
pre_compact_sync 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 pre_compact_sync 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 pre_compact_sync. 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.
pre_compact_sync is provided by the Session Buddy MCP server (lesleslie/session-buddy). 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 →