# delete_workspace_item

删除工作区中的文件或目录。 目录会被递归删除。不能删除工作区根目录。 路径必须在已绑定的工作区范围内。 ⚠️ 此操作不可逆，请确认后再调用。

Agent View of the PolicyLayer registry record for `delete_workspace_item`. HTML page: https://policylayer.com/tools/deepractice-promptx/delete-workspace-item

## Facts

- Tool: `delete_workspace_item`
- Server: PromptX (`deepractice/promptx`) — https://policylayer.com/tools/deepractice-promptx.md
- Homepage: https://github.com/Deepractice/PromptX
- Risk category: Destructive (Critical risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Hidden

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "delete_workspace_item",
    "arguments": {}
  }
}
```

## Why delete_workspace_item is rated Critical

This tool irreversibly deletes files and directories with recursive capability. It explicitly warns that the operation cannot be undone. Destructive category applies because the action cannot be reversed, and the blast radius is high—accidental or malicious deletion of workspace data could cause significant harm.

From the tool's own definition: "Tool name is 'delete_workspace_item'; description states '删除工作区中的文件或目录' (delete files or directories in workspace), '目录会被递归删除' (directories will be recursively deleted), and critically '此操作不可逆' (this operation is irreversible)."

## Use case

AI agents call delete_workspace_item to permanently remove resources in PromptX, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

## Recommended policy (PolicyLayer)

Verdict: **Hidden**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches PromptX:

```json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "delete_workspace_item"
  ]
}
```

## Other tools on PromptX (13)

- `toolx` — Execute — https://policylayer.com/tools/deepractice-promptx/toolx.md
- `learn` — Read — https://policylayer.com/tools/deepractice-promptx/learn.md
- `list_workspace_directory` — Read — https://policylayer.com/tools/deepractice-promptx/list-workspace-directory.md
- `list_workspaces` — Read — https://policylayer.com/tools/deepractice-promptx/list-workspaces.md
- `list_xlsx_sheets` — Read — https://policylayer.com/tools/deepractice-promptx/list-xlsx-sheets.md
- `read_docx` — Read — https://policylayer.com/tools/deepractice-promptx/read-docx.md
- `read_pdf` — Read — https://policylayer.com/tools/deepractice-promptx/read-pdf.md
- `read_pptx` — Read — https://policylayer.com/tools/deepractice-promptx/read-pptx.md
- `read_workspace_file` — Read — https://policylayer.com/tools/deepractice-promptx/read-workspace-file.md
- `read_xlsx` — Read — https://policylayer.com/tools/deepractice-promptx/read-xlsx.md
- `create_workspace_directory` — Write — https://policylayer.com/tools/deepractice-promptx/create-workspace-directory.md
- `project` — Write — https://policylayer.com/tools/deepractice-promptx/project.md
- `write_workspace_file` — Write — https://policylayer.com/tools/deepractice-promptx/write-workspace-file.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=deepractice-promptx · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/deepractice-promptx