手动触发数据归档。将指定天数之前的记录从主表移入归档表，以减少主表体积。可归档 messages（默认 30 天前）或 audit_log（默认 90 天前）。仅 admin 可调用。
AI agents call archive_data to permanently remove resources in Agent-Comm-Hub — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Archiving moves records out of the primary tables, making them inaccessible through normal queries and potentially irreversible depending on archive retention policies. While not a hard delete, it is a destructive reorganization of live data — records are removed from main tables and the operation may not be easily undone. The admin-only restriction signals high blast radius.
From the tool's definition 将指定天数之前的记录从主表移入归档表 (moves records from main table to archive table); 减少主表体积 (reduce main table size); 仅 admin 可调用 (admin-only)
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
手动触发数据归档。将指定天数之前的记录从主表移入归档表，以减少主表体积。可归档 messages（默认 30 天前）或 audit_log（默认 90 天前）。仅 admin 可调用。. It is categorised as a Destructive tool in the Agent-Comm-Hub MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Agent-Comm-Hub MCP server in PolicyLayer and add a rule for archive_data: 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 Agent-Comm-Hub. Nothing to install.
archive_data is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the archive_data 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 archive_data. 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.
archive_data is provided by the Agent-Comm-Hub MCP server (liuboacean/agent-comm-hub). 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 →