Asset Import

Check browse_assets first when a file may already be imported.

Grok Bot normally runs on a cloud computer. First confirm that the host exposes readable bytes for the requested attachment; a chat attachment card alone does not establish a filesystem path. If bytes are unavailable, use the host's supported file handoff with the user's permission, without scanning unrelated files or bypassing a denied transfer.

A ChatCut tab on the user's laptop cannot reach the cloud computer's loopback server. Use the upload-helper route unless the editor browser and source files are confirmed to share the same computer and network namespace. Follow the host's local-execution and file-transfer permissions.

Same-machine editor import (preferred)

1. Open the target project using browserHandoff.url or editorUrl. Keep exactly one editor tab for this project open, on the same machine/network namespace as your shell. A remote sandbox's localhost is not the user's localhost.
2. Start the bundled server using the host's bundled Node runtime when available, otherwise Node 18+ from PATH, and the origin of the actual editor URL:

"<bundled-or-global-node>" <this-skill-dir>/scripts/serve-local-media.mjs --origin <editor-origin> /path/to/source.mp4

Keep this process alive using the host's background-process support while calling MCP. It prints one JSON line and automatically exits after 900 seconds. It serves only the listed files over loopback URLs without an access token. URLs use the public chatcut-local-media-v1 path prefix to remain compatible with existing editors. Legacy token-prefixed URLs remain supported; the JSON token field contains that public prefix, not a credential.

3. Import multiple files in one import_media call: {"action":"from_editor","files":[...]}. Copy each file's assetId, url, filename, and sizeBytes from the printed imports array into files, omitting its per-file action. Each URL may come from a different running helper. Send 1–16 files per call; for larger sets, submit successive batches of 16. Up to eight files are processed concurrently; the editor streams each one straight into its local store, so a card with transfer progress appears as soon as the download starts. There is no loopback-specific file-size cap. The original top-level single-file arguments still work.
4. Inspect every entry in results: successful entries have ok:true and status:"locally_imported"; failed entries have an error. Results preserve input order and include assetId and filename, with top-level succeeded/failed counts. Retry only failed files with the same asset IDs. Success means the editor has persisted local bytes and registered the asset locally. Stop the helpers only after all files succeed. Keep the editor open for server sync, background upload and transcription.
5. Use the returned asset IDs for timeline work. Wait on track_progress target:"transcription" before transcript/caption work. Browser-renderable timelines defer original-file uploads; cloud-only or unsupported timelines upload automatically. Check browse_assets before waiting on target:"upload"; a deferred upload is not in progress. Use the editor's Upload action when cloud bytes are needed, preserving the same asset ID. If server sync is still catching up, retry the asset lookup.

On timeout, check browse_assets and retry with the same assetId; the import may still be running, and a retry resumes an interrupted download from where it stopped rather than starting over. Keep the same ID even if restarting the helper changes its URL. Do not blindly start a second import. Allow the editor's browser local-network permission if prompted. If the editor cannot reach the helper or the bridge is unavailable, use the fallback. A host-policy denial is not permission to try another transfer route.

For visual analysis, inspect readable original files locally rather than waiting for cloud upload. Import original source assets; do not flatten an edit into a local pre-render.

Relink an existing asset

For missing local media, preserve the existing asset and its timeline references:

1. Get the existing assetId from browse_assets and locate its corresponding original source file.
2. Serve that file with the same loopback helper above.
3. Call import_media with the helper's url, filename, and sizeBytes, but set action: "relink_from_editor" and replace the generated assetId with the existing assetId. For multiple files, use the same files array form, with an existing asset ID in every entry.
4. Wait for status: "locally_relinked" before stopping the helper. Upload/transcription may still be pending; keep the editor open.

Relink always reads the supplied file, even if the editor has cached bytes. The media type must match. Use the corresponding original, not a different replacement clip: relink preserves existing edits and transcripts. If the target is missing from the editor, let project sync finish and retry. A failed relink must not fall back to creating a new asset.

Upload-helper fallback

For a remote sandbox, unavailable editor, or blocked browser connection:

This route requires Node.js 18+, ffmpeg, and ffprobe on the computer running the helper. No media-tool binaries are bundled in this plugin. If these tools are unavailable, report the dependency and use the ChatCut editor upload flow; do not claim that Node alone is enough or install software silently.

1. Download a public URL to a local file when needed.
2. Call import_media with {"action":"create_session"}.
3. Run this skill's scripts/upload-media.mjs once with the returned token and endpoint and at most four local files. Split larger sets into batches of four and create one session per batch.

"<bundled-or-global-node>" <this-skill-dir>/scripts/upload-media.mjs --token <token> --endpoint <endpoint> /path/to/source-1.mp4 /path/to/source-2.wav

Resolve the helper relative to this skill; do not search the workspace. Run it in the foreground and read its final JSON from stdout. Do not detach it or invent status files. Do not replace it with handwritten ffprobe, ffmpeg, curl, metadata, transcode, or presigned-upload commands. MCP OAuth stays inside the MCP client; only the short-lived import token goes to the helper. Media bytes upload directly to storage and must not pass through the ChatCut backend.

Use each returned imports[].result.assetId for timeline work. Wait for track_progress target transcription before transcript or caption work. Wait for target upload only before byte-dependent work such as cloud export, request_asset_download, or remote frame inspection.

If the helper returns an error with retry, create a fresh import session when requested and rerun exactly the returned arguments. If host policy denies transfer of the user's file, stop instead of trying a local-editing or alternate-upload workaround; tell the user the upload was denied and ask them to use the ChatCut editor upload UI or grant the required permission.

Download an existing source

Follow the delivery contract returned by request_asset_download. A URL marked as a user-authenticated download belongs in the user's signed-in browser; Grok's cloud shell does not share that browser session. An unauthenticated HTTP 401 from that URL is not evidence that the MCP connection expired. Do not extract browser cookies or substitute a raw storage URL. For agent inspection, use readable original bytes or the supported inspect_asset path. Only download directly when the tool explicitly returns an agent-readable signed URL.