Weftly

Find & cut horizontal and vertical video clips (Shorts/Reels), transcribe & summarize.

CommunityDegradedNo sign-inGlobalFreeRead-only

What it can do

    What data it sees

    Do you need an account

    No: the server works without sign-in

    Find & cut horizontal and vertical video clips (Shorts/Reels), transcribe & summarize. Pay per job.

    How to connect

    How to connect Weftly to Claude

    The server address to paste into Claude settings:

    https://api.weftly.ai/mcp

    1. Open Claude (claude.ai or the desktop app).
    2. Go to Settings → Connectors.
    3. Click Add custom connector.
    4. Paste the server address copied below into Remote MCP server URL and click Add.
    5. In a chat, click + → Connectors and switch the new connector on.

    Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

    Authorization

    After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

    How to connect Weftly to ChatGPT

    The server address to paste into ChatGPT settings:

    https://api.weftly.ai/mcp

    1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
    2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
    3. Open Settings → Connectors and click Create.
    4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
    5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
    6. In a new chat open + → Apps/Connectors and enable the connector.

    OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

    Authorization

    On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

    How to connect Weftly to Cursor

    The server address to paste into Cursor settings:

    https://api.weftly.ai/mcp

    Fastest: click Open in Cursor below and confirm the prompt.

    Manually:

    1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
    2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
    3. Save the file. The server appears in the MCP list; authorize it there if asked.

    Authorization

    If the service needs sign-in, an authorize button appears next to the server in the MCP list.

    Server tool list (13)

    Raw names from tools/list. Only developers need these.

    transcribeTranscribe audio or video to text, including per-word timestamps for precise editing. Three-call flow: (1) call with `filename` to receive {job_id, payment_challenge}; (2) pay via MPP, then call with `job_id` + `payment_credential` to receive {upload_url} (presigned PUT, 1h expiry); (3) PUT the bytes, then complete_upload(job_id), then poll get_job_status(job_id). On completion, get_job_status returns two outputs: role `transcript` (SRT) and role `transcript-words` (JSON matching /.well-known/weftly-transcript-v2.schema.json, with segment-level and per-word timestamps). For other formats, pass `format=srt|txt|vtt|json|words` to get_job_status to receive content inline — `txt` and `vtt` are derived from SRT, `json` is v1 (segments only), `words` is v2 (segments + words). Flat price: audio $0.50, video $1.00 — see /.well-known/mpp.json for the authoritative table. Use for podcasts, interviews, meetings, lectures, and especially for creating clips, multicamera edits, or edit-video-from-transcript where word boundaries matter. Retrying any call with `job_id` alone returns current state (idempotent). Failed jobs auto-refund.
    summarizeSummarize an audio or video file — returns both a text summary AND the full transcript (with per-word timestamps). Do not also call transcribe on the same file. Three-call flow: (1) call with `filename` to receive {job_id, payment_challenge}; (2) pay via MPP, then call with `job_id` + `payment_credential` to receive {upload_url} (presigned PUT, 1h expiry); (3) PUT the bytes, then complete_upload(job_id), then poll get_job_status(job_id). On completion, get_job_status returns three outputs: role `summary` (plain text), role `transcript` (SRT), and role `transcript-words` (JSON matching /.well-known/weftly-transcript-v2.schema.json, with segment-level and per-word timestamps). For other formats, pass `format=srt|txt|vtt|json|words` to get_job_status to receive transcript content inline — `txt` and `vtt` are derived from SRT, `json` is v1 (segments only), `words` is v2 (segments + words). Flat price: audio $0.75, video $1.25 — see /.well-known/mpp.json for the authoritative table. Use for meetings, long-form interviews, lectures, and podcast episodes; the `words` output additionally supports creating clips, multicamera edits, or edit-video-from-transcript. Retrying any call with `job_id` alone returns current state (idempotent). Failed jobs auto-refund.
    find_clipsSTART HERE for any clip workflow on a video — `find_clips` is the canonical entry point and includes a full transcription as a free byproduct. **Do not call `transcribe` first**: doing so doubles the upload, doubles the spend, and produces the same transcript. Identify ranked candidate clips in a video — what to cut for highlights, social, or testimonials. Three-call flow: (1) call with `filename` (and optional `query`) to receive {job_id, payment_challenge}; (2) pay via MPP, then call with `job_id` + `payment_credential` to receive {upload_url} (presigned PUT, 1h expiry); (3) PUT the bytes, then complete_upload(job_id), then poll get_job_status(job_id). On completion, get_job_status returns three outputs: role `clip-candidates` (JSON matching /.well-known/weftly-clips-v1.schema.json — includes `source_job_id` and `source_expires_at`), role `transcript` (SRT, free byproduct), role `transcript-words` (JSON matching /.well-known/weftly-transcript-v2.schema.json, free byproduct). Each candidate carries `transcript_text` — the full text of what's in the clip — so callers can preview content before paying for extract_clip. Optional `query` parameter switches to query mode (e.g., "they discuss pricing", "the part about hiring") with the same output shape; the `mode` field in clip-candidates.json indicates which mode produced the result. Flat price: $2.00 video — see /.well-known/mpp.json. **Source-reuse contract:** the source video stays in storage for 72h after find_clips completes. Hand the find_clips `job_id` (also returned as `source_job_id` in the candidates JSON) to `extract_clip` or `extract_vertical_clip` as their `source_job_id` — within those 72h they cut directly from the stored source: no re-upload, no re-transcribe, just $0.50 per cut. Pass the same `source_job_id` to as many extract calls as you need. Use for interviews, podcasts, sales calls, all-hands recordings. Retrying with `job_id` alone returns current state. Failed jobs auto-refund.
    extract_clipCut and assemble a clip from any prior video job (find_clips, summarize, or video transcribe). Operates on a parent job — possessing the parent `source_job_id` is the capability, no upload step. Pass one segment for a simple cut, or multiple non-contiguous segments to compose a single mp4 highlight reel — same flat $0.50 either way. Two-call flow: (1) call with `source_job_id` + `segments` (ordered array of `{start, end, label?}` in source seconds, total duration capped at 30 minutes) to receive {job_id, payment_challenge}; (2) pay via MPP and call with `job_id` + `payment_credential` to start processing. No upload step. Poll get_job_status(job_id) for completion; outputs are role `clip-video` (the assembled .mp4, frame-accurate boundaries with 15ms audio fades at segment joins; audio loudness-normalized to -14 LUFS / -1.5 dBTP for clean, consistent playback) and — when `include_transcript: true` (default) — roles `clip-srt` + `clip-words` (transcripts stitched and time-shifted to match the assembled video). Set `include_transcript: false` to skip transcript outputs. Payment: pay by credit card via the Stripe Checkout link (open the returned `payment_url` in any browser) or Tempo USDC via mppx; the challenge's WWW-Authenticate header and /.well-known/mpp.json are authoritative for which methods are offered. Source must still be in storage (72h TTL for find_clips parents, 24h elsewhere — check `expires_at` from get_job_status on the parent). Multiple extract_clip calls against one parent are independent paid jobs. Failed jobs auto-refund.
    extract_vertical_clipCut a 9:16 vertical clip from any prior video job (find_clips, summarize, or video transcribe), suitable for direct upload to TikTok, Instagram Reels, or YouTube Shorts. Default output is 1080×1920 H.264 / AAC `.mp4` with center-cropped framing; audio loudness-normalized to -14 LUFS / -1.5 dBTP for short-form social. Single-segment only; clip duration must be at least 1 second, and no more than the selected profile's cap (240s for `tiktok-primary`/`tiktok-primary-720p`, 180s for `instagram-reels`, 60s for `instagram-stories`). Operates on a parent job — possessing the parent `source_job_id` is the capability, no upload step. Two-call flow: (1) call with `source_job_id` + `start` + `end` (in source seconds) to receive {job_id, payment_challenge}; (2) pay via MPP and call with `job_id` + `payment_credential` to start processing. Poll get_job_status(job_id) for completion; output is role `clip-vertical-video` (the `.mp4`). Flat price: $0.50 per clip. Payment: pay by credit card via the Stripe Checkout link (open the returned `payment_url` in any browser) or Tempo USDC via mppx. Optional `profile` parameter selects the encoding profile (default `tiktok-primary`). Allowed values: `tiktok-primary` (1080×1920, fast preset, CRF 22), `tiktok-primary-720p` (720×1280, CBR 3 Mbps — half-resolution mobile-optimized, ~40% faster wall time), `instagram-reels` (1080×1920, slow preset, CBR 4 Mbps), `instagram-stories` (same encode shape as instagram-reels). All four profiles loudness-normalize identically. Optional `subject` parameter controls reframing (default `center`, preserves today's behavior): `auto` locks onto the longest-tracked face from the parent's subjects-sidecar (or runs inline detection if the parent has none); `subject_id` (with `subject_id` param naming a face_N from the sidecar) locks onto a specific subject; `follow` switches crop between active speakers across the clip using the sidecar's active_speaker_timeline; `manual` accepts caller-supplied framing via `sub
    clips_verticalBatch-cut a set of your own chosen vertical 9:16 clips from a prior find_clips job in one purchase. Two-call flow: (1) call with `source_job_id` (a find_clips job id) and `clips` (1-5 objects `{start, end, title?}` in source seconds — your own picks from that job's `clip-candidates` output; nothing is auto-selected) to receive {job_id, payment_challenge}; (2) pay by credit card via the returned `payment_url` or Tempo USDC via mppx, then call again with `job_id` + `payment_credential` to start processing. Poll get_job_status(job_id); outputs are roles `clip-1-video` through `clip-N-video` (one 1080×1920 .mp4 per requested clip, loudness-normalized to -14 LUFS / -1.5 dBTP) plus `clips-manifest` (JSON) recording each clip's timing, output role, and any per-clip failure — a batch delivering fewer than N clips is not refunded, only one delivering zero is. Price: N × $0.50 per clip, charged once for the whole batch (Stripe quantity) rather than once per clip — see /.well-known/mpp.json for the Tempo USDC rate. Optional `profile` (default `tiktok-primary`; also `tiktok-primary-720p`, `instagram-reels`, `instagram-stories`) and `subject` (default `follow`, switches crop between active speakers; `auto` and `center` are opt-outs) apply to every clip in the batch. Use this once find_clips has surfaced candidates you like, to cut several in one purchase instead of one extract_vertical_clip call per clip; use extract_vertical_clip directly instead when you need per-clip framing control or more than 5 clips from one source. Source must still be in storage — check `expires_at` on the find_clips parent via get_job_status. Retrying with `job_id` alone recovers the current state.
    clips_horizontalBatch-cut a set of your own chosen horizontal 16:9 clips from a prior find_clips job in one purchase, delivered as SEPARATE files. Two-call flow: (1) call with `source_job_id` (a find_clips job id) and `clips` (1-5 objects `{start, end, title?}` in source seconds — your own picks from that job's `clip-candidates` output; nothing is auto-selected) to receive {job_id, payment_challenge}; (2) pay by credit card via the returned `payment_url` or Tempo USDC via mppx, then call again with `job_id` + `payment_credential` to start processing. Poll get_job_status(job_id); outputs are roles `clip-1-video` through `clip-N-video` (one .mp4 per requested clip, source framing and resolution preserved) plus `clips-manifest` (JSON) recording each clip's timing, output role, and any per-clip failure — a batch delivering fewer than N clips is not refunded, only one delivering zero is. Price: N × $0.50 per clip, charged once for the whole batch (Stripe quantity) rather than once per clip — see /.well-known/mpp.json for the Tempo USDC rate. No `profile` or `subject` parameters: horizontal keeps the source framing, so there is no crop to aim. **Choose deliberately between this and extract_clip**: extract_clip with several `segments` concatenates them into ONE highlight reel at the single-clip price, while this cuts N SEPARATE files at N × that price. Use this when each moment stands alone; use extract_clip when you want one file, need per-clip transcripts, or need more than 5 moments from one source. Use clips_vertical instead for 9:16 social output. Source must still be in storage — check `expires_at` on the find_clips parent via get_job_status. Retrying with `job_id` alone recovers the current state.
    complete_uploadConfirm that the file has been uploaded (via HTTP PUT to the upload_url from transcribe or summarize) and start processing. Verifies that the file is present in storage and that the job has been paid. Returns status "processing". Poll get_job_status to track progress and retrieve download URLs when done.
    get_job_statusCheck the status of a transcribe or summarize job. Returns the current state and, when completed, an `outputs` array. Each output has either `content` (returned inline) or a presigned, time-limited (1 hour) `download_url`. Small text outputs (e.g. `transcript` SRT, `clip-candidates`, `summary`) come inline as `content`; larger outputs — `transcript-words` JSON for any non-trivial recording, plus video outputs like `clip-video` / `clip-vertical-video` — come as a `download_url` to fetch when needed. Optionally pass `format` (srt, txt, vtt, json, words) to get the transcript content inline in the top-level `transcript` field — `txt` and `vtt` are derived from the stored SRT; `json` is v1 (segments only); `words` is v2 (segments + per-word timestamps matching /.well-known/weftly-transcript-v2.schema.json). Poll this periodically after calling complete_upload — wait at least 60 seconds between checks. For files under 10 minutes, jobs usually complete within 1-2 minutes. For long files (1hr+), expect 10-30 minutes. Derivative jobs (`extract_clip`, `extract_vertical_clip`, `publish_youtube`, `clips_vertical`, `clips_horizontal`) have no upload step and no `awaiting_upload`/`awaiting_complete_upload` states — a paid derivative job reports `processing` once its parent source is confirmed still in storage, or a terminal `source_expired` if the parent source has expired: stop polling, and re-run the parent job named in `source_job_id` to get a fresh source before retrying. Also use this to recover from lost state: if the original challenge was lost, call get_job_status(job_id) to retrieve a fresh challenge (status "awaiting_payment") or the upload URL (status "awaiting_upload").
    mpp_smoke_testSmoke-test the MPP payment plumbing end-to-end via this MCP server, for $0.01 USDC. Two-call flow: (1) call with no arguments to receive an MPP `payment_challenge`; (2) pay via MPP and call again with `payment_credential` set to the resulting Authorization header value (e.g. "Payment eyJ...") to receive {paid: true, timestamp, receipt_ref, payment_method}. Uses the exact same `createPayToAddress` + `createMppHandler` verification path as paid product tools (transcribe, summarize), so a green run here means real paid calls will work too. Stateless — no job is created, no database row written. Use this whenever you want to confirm a wallet, the MCP transport, the worker, and the production payment middleware are all healthy without paying a transcribe price. Cost: $0.01 USDC per attempt.
    publish_to_youtubePublish an existing video from a transcribe or summarize job to YouTube. Creates a paid publish job (flat $1.75 price) and stores the OAuth token. Captions are auto-generated from the session transcript if available. Workflow: create_job → pay → trigger_youtube_publish → poll get_youtube_publish_status. Requires a YouTube OAuth2 access token obtained independently via Google OAuth (scope: youtube.upload).
    trigger_youtube_publishStart the YouTube upload after payment is confirmed. Call this after publish_to_youtube once payment_status is "paid". Returns immediately — the upload runs as a durable Workflow in the background. Poll get_youtube_publish_status to track progress.
    get_youtube_publish_statusCheck the status of a YouTube publish job. Poll periodically after trigger_youtube_publish — the upload takes 1-10 minutes depending on video size. Returns status (pending, publishing, completed, failed) and the youtube_video_url once complete.