# images_delete

删除图片素材 (Delete image)

Agent View of the PolicyLayer registry record for `images_delete`. HTML page: https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp/images-delete

## Facts

- Tool: `images_delete`
- Server: Tencent Ad MCP Server (`andyleimc-source/tencent-ad-mcp`) — https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp.md
- Homepage: https://github.com/andyleimc-source/tencent-ad-mcp
- 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": "images_delete",
    "arguments": {}
  }
}
```

## Why images_delete is rated Critical

This tool permanently removes image assets from the user's Tencent Ads account. Deletion is irreversible and cannot be undone. An AI agent could maliciously or accidentally delete valuable marketing creative assets, causing business disruption and loss of campaign materials. This qualifies as Destructive rather than Write (which is reversible) or Execute (which has variable effects).

From the tool's own definition: "Tool name: images_delete. Description: '删除图片素材' translates to 'Delete image' or 'Delete image material/assets'. The verb 'delete' combined with the object 'image' clearly indicates irreversible removal of data."

## Use case

AI agents call images_delete to permanently remove resources in Tencent Ad MCP Server, 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 Tencent Ad MCP Server:

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

## Other tools on Tencent Ad MCP Server (356)

- `adgroups_delete` — Destructive — https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp/adgroups-delete.md
- `bidword_delete` — Destructive — https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp/bidword-delete.md
- `channels_comment_delete` — Destructive — https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp/channels-comment-delete.md
- `components_delete` — Destructive — https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp/components-delete.md
- `custom_audiences_delete` — Destructive — https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp/custom-audiences-delete.md
- `dynamic_creatives_delete` — Destructive — https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp/dynamic-creatives-delete.md
- `live_room_components_delete` — Destructive — https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp/live-room-components-delete.md
- `local_store_packages_delete` — Destructive — https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp/local-store-packages-delete.md
- `local_stores_delete` — Destructive — https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp/local-stores-delete.md
- `marketing_target_assets_delete` — Destructive — https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp/marketing-target-assets-delete.md
- `material_labels_delete` — Destructive — https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp/material-labels-delete.md
- `official_landing_page_delete` — Destructive — https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp/official-landing-page-delete.md
- `product_items_delete` — Destructive — https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp/product-items-delete.md
- `profiles_delete` — Destructive — https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp/profiles-delete.md
- `programmed_commponent_preview_delete` — Destructive — https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp/programmed-commponent-preview-delete.md
- `qualifications_delete` — Destructive — https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp/qualifications-delete.md
- `rtatarget_bind_delete` — Destructive — https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp/rtatarget-bind-delete.md
- `rtatarget_delete` — Destructive — https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp/rtatarget-delete.md
- `union_position_packages_delete` — Destructive — https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp/union-position-packages-delete.md
- `videos_delete` — Destructive — https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp/videos-delete.md
- `wechat_channels_ad_account_delete` — Destructive — https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp/wechat-channels-ad-account-delete.md
- `wechat_channels_authorization_delete` — Destructive — https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp/wechat-channels-authorization-delete.md
- `wechat_pages_delete` — Destructive — https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp/wechat-pages-delete.md
- `xijing_page_delete` — Destructive — https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp/xijing-page-delete.md
- `async_tasks_add` — Execute — https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp/async-tasks-add.md
- `batch_async_requests_add` — Execute — https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp/batch-async-requests-add.md
- `batch_requests_add` — Execute — https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp/batch-requests-add.md
- `leads_voip_call_add` — Execute — https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp/leads-voip-call-add.md
- `material_async_tasks_add` — Execute — https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp/material-async-tasks-add.md
- `fund_transfer_add` — Financial — https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp/fund-transfer-add.md
- …and 326 more: https://policylayer.com/tools/andyleimc-source-tencent-ad-mcp.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=andyleimc-source-tencent-ad-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/andyleimc-source-tencent-ad-mcp