# delete

Permanently delete; irreversible, so confirm with the user first. project: it and everything in it. asset: a character, environment or object. music_track: a background music track. segment_extra: a segment's sound effect or overlay, with its scene layers. A segment's image, clip and voiceover can't be deleted.

Agent View of the PolicyLayer registry record for `delete`. HTML page: https://policylayer.com/tools/com-framesail-framesail/delete

## Facts

- Tool: `delete`
- Server: Framesail (`https://api.framesail.com/mcp`) — https://policylayer.com/tools/com-framesail-framesail.md
- Homepage: https://github.com/https://api.framesail.com/mcp
- Risk category: Destructive (Critical risk)
- Registry record: grade F, identity unverified
- Server auth posture: open
- Server rate-limited: no
- Parameters: 4 (1 required)
- Recommended policy verdict: Hidden

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `id` | object | no | The asset, music track, or segment sound effect or overlay |
| `type` | string | yes | project: project_id; asset, music_track: id; segment_extra: project_id, segment_number, and id if the segment has several |
| `project_id` | object | no | Project id |
| `segment_number` | object | no | Segment number (1-based, from storyboard_read) |

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",
    "arguments": {
      "type": "<type>"
    }
  }
}
```

## Why delete is rated Critical

An AI agent that decides to call delete doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from Framesail is gone. There is no undo for destructive operations.

Risk signals: Bulk/mass operation — affects multiple targets

## Use case

AI agents call delete to permanently remove resources in Framesail, 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 Framesail:

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

## Other tools on Framesail (27)

- `render` — Execute — https://policylayer.com/tools/com-framesail-framesail/render.md
- `assets_read` — Read — https://policylayer.com/tools/com-framesail-framesail/assets-read.md
- `editor_read` — Read — https://policylayer.com/tools/com-framesail-framesail/editor-read.md
- `get_generation_options` — Read — https://policylayer.com/tools/com-framesail-framesail/get-generation-options.md
- `get_status` — Read — https://policylayer.com/tools/com-framesail-framesail/get-status.md
- `projects_read` — Read — https://policylayer.com/tools/com-framesail-framesail/projects-read.md
- `script_read` — Read — https://policylayer.com/tools/com-framesail-framesail/script-read.md
- `storyboard_read` — Read — https://policylayer.com/tools/com-framesail-framesail/storyboard-read.md
- `style_read` — Read — https://policylayer.com/tools/com-framesail-framesail/style-read.md
- `view_image` — Read — https://policylayer.com/tools/com-framesail-framesail/view-image.md
- `voiceover_read` — Read — https://policylayer.com/tools/com-framesail-framesail/voiceover-read.md
- `account_edit` — Write — https://policylayer.com/tools/com-framesail-framesail/account-edit.md
- `assets_edit` — Write — https://policylayer.com/tools/com-framesail-framesail/assets-edit.md
- `assets_generate` — Write — https://policylayer.com/tools/com-framesail-framesail/assets-generate.md
- `editor_edit` — Write — https://policylayer.com/tools/com-framesail-framesail/editor-edit.md
- `export_video` — Write — https://policylayer.com/tools/com-framesail-framesail/export-video.md
- `projects_edit` — Write — https://policylayer.com/tools/com-framesail-framesail/projects-edit.md
- `script_edit` — Write — https://policylayer.com/tools/com-framesail-framesail/script-edit.md
- `script_generate` — Write — https://policylayer.com/tools/com-framesail-framesail/script-generate.md
- `segment_edit` — Write — https://policylayer.com/tools/com-framesail-framesail/segment-edit.md
- `segment_restructure` — Write — https://policylayer.com/tools/com-framesail-framesail/segment-restructure.md
- `storyboard_edit` — Write — https://policylayer.com/tools/com-framesail-framesail/storyboard-edit.md
- `storyboard_generate` — Write — https://policylayer.com/tools/com-framesail-framesail/storyboard-generate.md
- `style_edit` — Write — https://policylayer.com/tools/com-framesail-framesail/style-edit.md
- `style_generate` — Write — https://policylayer.com/tools/com-framesail-framesail/style-generate.md
- `voiceover_edit` — Write — https://policylayer.com/tools/com-framesail-framesail/voiceover-edit.md
- `voiceover_generate` — Write — https://policylayer.com/tools/com-framesail-framesail/voiceover-generate.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=com-framesail-framesail · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/com-framesail-framesail