종합 데이터 삭제 도구 - 작업기억, 세션, 히스토리, 검색인덱스 등 카테고리별 세분화된 삭제 지원. 단일/복수/조건부/전체 삭제 가능
AI agents call delete_work_memory to permanently remove resources in Work Memory MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes persistent data across multiple categories (work memories, sessions, history, indexes). The capability to perform wholesale deletion ('전체 삭제') on structured work content and context cannot be undone. While the blast radius is limited to work memory data rather than critical systems, the irreversible nature and potential to wipe entire project contexts justifies the Destructive category.
From the tool's definition delete_work_memory is explicitly a deletion tool that supports 'category-specific segmented deletion' of work memories, sessions, history, and search indexes.
Documented attack patterns abuse exactly the kind of access delete_work_memory gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Work Memory MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_work_memory:
{
"version": "1",
"default": "deny",
"hide": [
"delete_work_memory"
]
} delete_work_memory disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
종합 데이터 삭제 도구 - 작업기억, 세션, 히스토리, 검색인덱스 등 카테고리별 세분화된 삭제 지원. 단일/복수/조건부/전체 삭제 가능. It is categorised as a Destructive tool in the Work Memory MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Work Memory MCP Server MCP server in PolicyLayer and add a rule for delete_work_memory: 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 Work Memory MCP Server. Nothing to install.
delete_work_memory 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 delete_work_memory 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 delete_work_memory. 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.
delete_work_memory is provided by the Work Memory MCP Server MCP server (moontmsai/work-memory-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Work Memory MCP Server, 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.
24 Work Memory MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.