# read_sequence_captions

Reads caption tracks of a sequence, returning each caption clip as { start, end, text } in seconds. IMPORTANT: Premiere Pro exposes no caption-read API in its scripting DOM, so in practice this returns trackCount:0 / captions:[] even when the sequence HAS a working caption track. The response field captionReadSupported:false (plus note) signals this — a 0 result does NOT mean the sequence has no captions. To read cue text/timing, parse the source .srt file directly instead.

Agent View of the PolicyLayer registry record for `read_sequence_captions`. HTML page: https://policylayer.com/tools/adobe-premiere-pro-mcp/read-sequence-captions

## Facts

- Tool: `read_sequence_captions`
- Server: Adobe Premiere Pro (`adobe-premiere-pro-mcp`) — https://policylayer.com/tools/adobe-premiere-pro-mcp.md
- Install: `npx -y adobe-premiere-pro-mcp`
- Homepage: https://www.npmjs.com/package/adobe-premiere-pro-mcp
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 1
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `sequenceId` | string | no | Optional sequence ID. Defaults to the active sequence. |

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": "read_sequence_captions",
    "arguments": {}
  }
}
```

## Why read_sequence_captions is rated Low

This tool retrieves caption metadata (start time, end time, text content) from a video sequence. It has no side effects, makes no modifications to the project, and poses minimal risk even if misused—at worst, an AI agent would read caption data it should not have access to.

From the tool's own definition: "Tool name contains 'read_', description states 'Reads caption tracks of a sequence, returning each caption clip as { start, end, text }'. The operation retrieves caption data without modifying, deleting, or executing external operations."

## Use case

AI agents call read_sequence_captions to retrieve information from Adobe Premiere Pro without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Adobe Premiere Pro:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "read_sequence_captions": {}
  }
}
```

## Other tools on Adobe Premiere Pro (282)

- `clear_item_in_out` — Destructive — https://policylayer.com/tools/adobe-premiere-pro-mcp/clear-item-in-out.md
- `clear_sequence_in_out` — Destructive — https://policylayer.com/tools/adobe-premiere-pro-mcp/clear-sequence-in-out.md
- `delete_bin` — Destructive — https://policylayer.com/tools/adobe-premiere-pro-mcp/delete-bin.md
- `delete_marker` — Destructive — https://policylayer.com/tools/adobe-premiere-pro-mcp/delete-marker.md
- `delete_multiple_project_items` — Destructive — https://policylayer.com/tools/adobe-premiere-pro-mcp/delete-multiple-project-items.md
- `delete_preview_files` — Destructive — https://policylayer.com/tools/adobe-premiere-pro-mcp/delete-preview-files.md
- `delete_project_item` — Destructive — https://policylayer.com/tools/adobe-premiere-pro-mcp/delete-project-item.md
- `delete_sequence` — Destructive — https://policylayer.com/tools/adobe-premiere-pro-mcp/delete-sequence.md
- `delete_track` — Destructive — https://policylayer.com/tools/adobe-premiere-pro-mcp/delete-track.md
- `remove_all_effects` — Destructive — https://policylayer.com/tools/adobe-premiere-pro-mcp/remove-all-effects.md
- `remove_effect` — Destructive — https://policylayer.com/tools/adobe-premiere-pro-mcp/remove-effect.md
- `remove_effect_by_name` — Destructive — https://policylayer.com/tools/adobe-premiere-pro-mcp/remove-effect-by-name.md
- `remove_from_timeline` — Destructive — https://policylayer.com/tools/adobe-premiere-pro-mcp/remove-from-timeline.md
- `remove_keyframe` — Destructive — https://policylayer.com/tools/adobe-premiere-pro-mcp/remove-keyframe.md
- `remove_keyframe_range` — Destructive — https://policylayer.com/tools/adobe-premiere-pro-mcp/remove-keyframe-range.md
- `remove_selected_clips` — Destructive — https://policylayer.com/tools/adobe-premiere-pro-mcp/remove-selected-clips.md
- `ripple_delete` — Destructive — https://policylayer.com/tools/adobe-premiere-pro-mcp/ripple-delete.md
- `add_to_render_queue` — Execute — https://policylayer.com/tools/adobe-premiere-pro-mcp/add-to-render-queue.md
- `auto_reframe_sequence` — Execute — https://policylayer.com/tools/adobe-premiere-pro-mcp/auto-reframe-sequence.md
- `build_brand_spot_from_mogrt_and_assets` — Execute — https://policylayer.com/tools/adobe-premiere-pro-mcp/build-brand-spot-from-mogrt-and-assets.md
- `build_motion_graphics_demo` — Execute — https://policylayer.com/tools/adobe-premiere-pro-mcp/build-motion-graphics-demo.md
- `execute_extendscript` — Execute — https://policylayer.com/tools/adobe-premiere-pro-mcp/execute-extendscript.md
- `export_sequence` — Execute — https://policylayer.com/tools/adobe-premiere-pro-mcp/export-sequence.md
- `open_project` — Execute — https://policylayer.com/tools/adobe-premiere-pro-mcp/open-project.md
- `set_playhead_position` — Execute — https://policylayer.com/tools/adobe-premiere-pro-mcp/set-playhead-position.md
- `start_batch_encode` — Execute — https://policylayer.com/tools/adobe-premiere-pro-mcp/start-batch-encode.md
- `stop_playback` — Execute — https://policylayer.com/tools/adobe-premiere-pro-mcp/stop-playback.md
- `undo` — Execute — https://policylayer.com/tools/adobe-premiere-pro-mcp/undo.md
- `consolidate_and_transfer` — Financial — https://policylayer.com/tools/adobe-premiere-pro-mcp/consolidate-and-transfer.md
- `check_offline_media` — Read — https://policylayer.com/tools/adobe-premiere-pro-mcp/check-offline-media.md
- …and 252 more: https://policylayer.com/tools/adobe-premiere-pro-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=adobe-premiere-pro-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/adobe-premiere-pro-mcp