清理指定任务及其相关数据
AI agents call cleanup_task to permanently remove resources in Claude Code Multi-Process MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
'Cleanup' of a task and its related data implies irreversible deletion or purging of task records and associated data. Once cleaned up, the task history and related data are permanently removed and cannot be recovered, placing this in the Destructive category. Severity is medium because it affects task metadata/session data rather than production data or critical systems.
From the tool's definition 清理指定任务及其相关数据 (Clean up specified task and its related data)
Attacks that exploit this kind of access
清理指定任务及其相关数据. It is categorised as a Destructive tool in the Claude Code Multi-Process MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Claude Code Multi-Process MCP Server MCP server in PolicyLayer and add a rule for cleanup_task: 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 Code Multi-Process MCP Server. Nothing to install.
cleanup_task 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 cleanup_task 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 cleanup_task. 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.
cleanup_task is provided by the Claude Code Multi-Process MCP Server MCP server (l-x-c/cc-multi-process-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 →