# delete_site

Permanently delete an owned site. Irreversible — confirm with the user first.

Agent View of the PolicyLayer registry record for `delete_site`. HTML page: https://policylayer.com/tools/ai-dataecho-mcp/delete-site

## Facts

- Tool: `delete_site`
- Server: Mcp (`https://dataecho.ai/mcp`) — https://policylayer.com/tools/ai-dataecho-mcp.md
- Homepage: https://github.com/mohocp/dataecho
- Risk category: Destructive (Critical risk)
- Registry record: grade F, identity unverified
- Server auth posture: open
- Server CORS policy: *
- Server rate-limited: no
- Parameters: 1 (1 required)
- Recommended policy verdict: Hidden

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `slug` | string | yes | Site slug |

Parameters from the server's own tool schema.

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

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "delete_site",
    "arguments": {
      "slug": "<slug>"
    }
  }
}
```

## Why delete_site is rated Critical

This tool irreversibly removes a deployed site, destroying all associated data and configurations. While scoped to owned sites, an AI agent misusing this could cause significant unrecoverable damage to user deployments. The explicit irreversibility warning confirms the Destructive category is most appropriate, superseding any Write classification.

From the tool's own definition: "'Permanently delete an owned site. Irreversible — confirm with the user first.' The tool description explicitly states 'Permanently delete' and 'Irreversible', which are hallmarks of destructive operations that cannot be undone."

## Use case

AI agents call delete_site to permanently remove resources in Mcp, 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 Mcp:

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

## Other tools on Mcp (25)

- `delete_variable` — Destructive — https://policylayer.com/tools/ai-dataecho-mcp/delete-variable.md
- `drive_delete_file` — Destructive — https://policylayer.com/tools/ai-dataecho-mcp/drive-delete-file.md
- `drive_revoke_token` — Destructive — https://policylayer.com/tools/ai-dataecho-mcp/drive-revoke-token.md
- `app_status` — Read — https://policylayer.com/tools/ai-dataecho-mcp/app-status.md
- `drive_history` — Read — https://policylayer.com/tools/ai-dataecho-mcp/drive-history.md
- `drive_list_files` — Read — https://policylayer.com/tools/ai-dataecho-mcp/drive-list-files.md
- `drive_read_file` — Read — https://policylayer.com/tools/ai-dataecho-mcp/drive-read-file.md
- `drive_tokens` — Read — https://policylayer.com/tools/ai-dataecho-mcp/drive-tokens.md
- `get_site` — Read — https://policylayer.com/tools/ai-dataecho-mcp/get-site.md
- `list_drives` — Read — https://policylayer.com/tools/ai-dataecho-mcp/list-drives.md
- `list_sites` — Read — https://policylayer.com/tools/ai-dataecho-mcp/list-sites.md
- `list_variables` — Read — https://policylayer.com/tools/ai-dataecho-mcp/list-variables.md
- `platform_info` — Read — https://policylayer.com/tools/ai-dataecho-mcp/platform-info.md
- `search_sites` — Read — https://policylayer.com/tools/ai-dataecho-mcp/search-sites.md
- `verify_login_code` — Read — https://policylayer.com/tools/ai-dataecho-mcp/verify-login-code.md
- `claim_site` — Write — https://policylayer.com/tools/ai-dataecho-mcp/claim-site.md
- `create_drive` — Write — https://policylayer.com/tools/ai-dataecho-mcp/create-drive.md
- `drive_move_file` — Write — https://policylayer.com/tools/ai-dataecho-mcp/drive-move-file.md
- `drive_restore` — Write — https://policylayer.com/tools/ai-dataecho-mcp/drive-restore.md
- `drive_share` — Write — https://policylayer.com/tools/ai-dataecho-mcp/drive-share.md
- `drive_write_file` — Write — https://policylayer.com/tools/ai-dataecho-mcp/drive-write-file.md
- `publish_site` — Write — https://policylayer.com/tools/ai-dataecho-mcp/publish-site.md
- `request_login_code` — Write — https://policylayer.com/tools/ai-dataecho-mcp/request-login-code.md
- `set_variable` — Write — https://policylayer.com/tools/ai-dataecho-mcp/set-variable.md
- `update_site_metadata` — Write — https://policylayer.com/tools/ai-dataecho-mcp/update-site-metadata.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=ai-dataecho-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/ai-dataecho-mcp