Weftly

Official13 toolsLive

by weftly

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

ai.weftly/weftly (MCP Server)

The ai.weftly/weftly MCP server helps users find and cut horizontal and vertical video clips for Shorts/Reels, then transcribe and summarize the resulting content. It operates on a pay per job model, with 13 tools exposed for these tasks.

🛠️ Key Features

Find and cut horizontal and vertical video clips (Shorts/Reels)
Transcribe video content
Summarize transcriptions
Pay per job execution
13 available tools

🚀 Use Cases

Preparing Shorts/Reels by extracting specific horizontal or vertical segments
Converting video clips into text via transcription
Generating summaries from transcribed video content

⚡ Developer Benefits

Multiple tools (13) for the end-to-end workflow (find/cut → transcribe → summarize)
Fits pipeline use cases for Shorts/Reels content preparation

Captured live from the server via tools/list.

transcribe

Transcribe 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.

Parameters3

filename	string	optional	Filename with extension (e.g. "podcast.mp3"). Required on the first call — used to infer media type (audio vs video) and label outputs. Supported extensions: mp3, wav, m4a, ogg, flac, mp4, mov, webm, mkv.
job_id	string	optional	Job ID returned from a previous call. Include along with payment_credential to confirm payment and receive the presigned upload URL. Also include alone to recover the current challenge/state if the original response was lost.
payment_credential	string	optional	MPP payment credential (full Authorization header value, e.g. "Payment eyJ...") obtained by paying the challenge returned from the first call. Include with job_id to verify payment and receive the upload URL.

Raw schema

{
  "type": "object",
  "properties": {
    "filename": {
      "description": "Filename with extension (e.g. \"podcast.mp3\"). Required on the first call — used to infer media type (audio vs video) and label outputs. Supported extensions: mp3, wav, m4a, ogg, flac, mp4, mov, webm, mkv.",
      "type": "string"
    },
    "job_id": {
      "description": "Job ID returned from a previous call. Include along with payment_credential to confirm payment and receive the presigned upload URL. Also include alone to recover the current challenge/state if the original response was lost.",
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    },
    "payment_credential": {
      "description": "MPP payment credential (full Authorization header value, e.g. \"Payment eyJ...\") obtained by paying the challenge returned from the first call. Include with job_id to verify payment and receive the upload URL.",
      "type": "string"
    }
  },
  "additionalProperties": false
}

summarize

Summarize 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.

Parameters3

filename	string	optional	Filename with extension (e.g. "podcast.mp3"). Required on the first call — used to infer media type (audio vs video) and label outputs. Supported extensions: mp3, wav, m4a, ogg, flac, mp4, mov, webm, mkv.
job_id	string	optional	Job ID returned from a previous call. Include along with payment_credential to confirm payment and receive the presigned upload URL. Also include alone to recover the current challenge/state if the original response was lost.
payment_credential	string	optional	MPP payment credential (full Authorization header value, e.g. "Payment eyJ...") obtained by paying the challenge returned from the first call. Include with job_id to verify payment and receive the upload URL.

Raw schema

{
  "type": "object",
  "properties": {
    "filename": {
      "description": "Filename with extension (e.g. \"podcast.mp3\"). Required on the first call — used to infer media type (audio vs video) and label outputs. Supported extensions: mp3, wav, m4a, ogg, flac, mp4, mov, webm, mkv.",
      "type": "string"
    },
    "job_id": {
      "description": "Job ID returned from a previous call. Include along with payment_credential to confirm payment and receive the presigned upload URL. Also include alone to recover the current challenge/state if the original response was lost.",
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    },
    "payment_credential": {
      "description": "MPP payment credential (full Authorization header value, e.g. \"Payment eyJ...\") obtained by paying the challenge returned from the first call. Include with job_id to verify payment and receive the upload URL.",
      "type": "string"
    }
  },
  "additionalProperties": false
}

find_clips

START 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.

Parameters4

filename	string	optional	Filename with extension (e.g. "podcast.mp3"). Required on the first call — used to infer media type (audio vs video) and label outputs. Supported extensions: mp3, wav, m4a, ogg, flac, mp4, mov, webm, mkv.
job_id	string	optional	Job ID returned from a previous call. Include along with payment_credential to confirm payment and receive the presigned upload URL. Also include alone to recover the current challenge/state if the original response was lost.
payment_credential	string	optional	MPP payment credential (full Authorization header value, e.g. "Payment eyJ...") obtained by paying the challenge returned from the first call. Include with job_id to verify payment and receive the upload URL.
query	string	optional	Optional. Switches the analyzer from "best clips" discovery mode to query mode — finds segments matching this content (e.g., "they discuss pricing", "the part about hiring"). Same output shape either way; the `mode` field in clip-candidates.json tells consumers how to interpret per-candidate scoring.

Raw schema

{
  "type": "object",
  "properties": {
    "filename": {
      "description": "Filename with extension (e.g. \"podcast.mp3\"). Required on the first call — used to infer media type (audio vs video) and label outputs. Supported extensions: mp3, wav, m4a, ogg, flac, mp4, mov, webm, mkv.",
      "type": "string"
    },
    "job_id": {
      "description": "Job ID returned from a previous call. Include along with payment_credential to confirm payment and receive the presigned upload URL. Also include alone to recover the current challenge/state if the original response was lost.",
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    },
    "payment_credential": {
      "description": "MPP payment credential (full Authorization header value, e.g. \"Payment eyJ...\") obtained by paying the challenge returned from the first call. Include with job_id to verify payment and receive the upload URL.",
      "type": "string"
    },
    "query": {
      "description": "Optional. Switches the analyzer from \"best clips\" discovery mode to query mode — finds segments matching this content (e.g., \"they discuss pricing\", \"the part about hiring\"). Same output shape either way; the `mode` field in clip-candidates.json tells consumers how to interpret per-candidate scoring.",
      "type": "string",
      "minLength": 1,
      "maxLength": 500
    }
  },
  "additionalProperties": false
}

extract_clip

Cut 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.

Parameters6

source_job_id	string	optional	Job ID of any prior video job (find_clips, summarize, or video transcribe). Possessing this id is the capability — extract_clip is not session-bound, so a user can come back from a different session within the parent's TTL and still extract. Required on the first call.
segments	array	optional	Ordered array of source-relative segments to cut and concatenate into the output. Single segment for a simple cut; multiple segments compose a single mp4 from non-contiguous moments — same flat $0.50 either way. Total summed duration capped at 30 minutes per call. Required on the first call.
include_transcript	boolean	optional	Default true. When true, the pipeline writes clip-srt + clip-words outputs stitched to match the assembled video. Set false to skip and just receive the .mp4.
title	string	optional	Optional title for the assembled clip. Surfaces in get_job_status and download filenames; doesn't affect the cut itself.
job_id	string	optional	Job ID returned from a previous extract_clip call. Include along with payment_credential to confirm payment and trigger processing. Also include alone to recover the current state.
payment_credential	string	optional	MPP payment credential (full Authorization header value, e.g. "Payment eyJ..."). extract_clip accepts Tempo USDC and Stripe SPT — see the challenge's WWW-Authenticate header or /.well-known/mpp.json for the supported methods. Include with job_id after paying the challenge to start processing.

Raw schema

{
  "type": "object",
  "properties": {
    "source_job_id": {
      "description": "Job ID of any prior video job (find_clips, summarize, or video transcribe). Possessing this id is the capability — extract_clip is not session-bound, so a user can come back from a different session within the parent's TTL and still extract. Required on the first call.",
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    },
    "segments": {
      "description": "Ordered array of source-relative segments to cut and concatenate into the output. Single segment for a simple cut; multiple segments compose a single mp4 from non-contiguous moments — same flat $0.50 either way. Total summed duration capped at 30 minutes per call. Required on the first call.",
      "minItems": 1,
      "maxItems": 50,
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "start": {
            "type": "number",
            "minimum": 0,
            "description": "Source-relative start time in seconds."
          },
          "end": {
            "type": "number",
            "minimum": 0,
            "description": "Source-relative end time in seconds. Must be > start."
          },
          "label": {
            "description": "Optional label for this segment, surfaces in agent dialog.",
            "type": "string",
            "maxLength": 200
          }
        },
        "required": [
          "start",
          "end"
        ],
        "additionalProperties": false
      }
    },
    "include_transcript": {
      "description": "Default true. When true, the pipeline writes clip-srt + clip-words outputs stitched to match the assembled video. Set false to skip and just receive the .mp4.",
      "type": "boolean"
    },
    "title": {
      "description": "Optional title for the assembled clip. Surfaces in get_job_status and download filenames; doesn't affect the cut itself.",
      "type": "string",
      "maxLength": 200
    },
    "job_id": {
      "description": "Job ID returned from a previous extract_clip call. Include along with payment_credential to confirm payment and trigger processing. Also include alone to recover the current state.",
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    },
    "payment_credential": {
      "description": "MPP payment credential (full Authorization header value, e.g. \"Payment eyJ...\"). extract_clip accepts Tempo USDC and Stripe SPT — see the challenge's WWW-Authenticate header or /.well-known/mpp.json for the supported methods. Include with job_id after paying the challenge to start processing.",
      "type": "string"
    }
  },
  "additionalProperties": false
}

extract_vertical_clip

Cut 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 `subject_box: {x, y, w, h}` (source pixels) or `subject_x_offset` (direct crop x). Sidecar shape at /.well-known/weftly-subjects-v1.schema.json. auto/subject_id/follow fall back to center if detection or sidecar resolution fails — the paid job always delivers a clip. Source must be a horizontal video (wider than 9:16) — already-vertical or square sources are rejected. Source must still be in storage (72h TTL for find_clips parents, 24h elsewhere — check `expires_at` from get_job_status on the parent). Pair with `find_clips` ($2.00/video) to pick a moment first, then call this to get a download-ready vertical mp4 in under 5 minutes. Multiple extract_vertical_clip calls against one parent are independent paid jobs. Failed jobs auto-refund.

Parameters12

source_job_id	string	optional	Job ID of any prior video job (find_clips, summarize, or video transcribe). Possessing this id is the capability — extract_vertical_clip is not session-bound, so a user can come back from a different session within the parent's TTL and still extract. Required on the first call.
start	number	optional	Source-relative start time in seconds. Required on the first call.
end	number	optional	Source-relative end time in seconds (must be > start; end - start must be at least 1s, and no more than the selected profile's cap — 240s for tiktok-primary/tiktok-primary-720p, 180s for instagram-reels, 60s for instagram-stories). Required on the first call.
title	string	optional	Optional title for the assembled clip. Surfaces in get_job_status and download filenames; doesn't affect the cut itself.
profile	string	optional	Optional encoding profile. Default: tiktok-primary (1080×1920 H.264 fast preset, CRF 22, 6 Mbps cap). tiktok-primary-720p: 720×1280, CBR 3 Mbps — half-resolution mobile-optimized, ~40% faster wall time. instagram-reels: 1080×1920 H.264 slow preset, CBR 4 Mbps. instagram-stories: same encode shape as instagram-reels. All four apply loudness normalization to -14 LUFS / -1.5 dBTP.
subject	string	optional	Optional reframing strategy. Default: "center" (hardcoded center crop, today's behavior). "auto": lock onto the longest-tracked face from the parent find_clips job's subjects-sidecar (or run inline detection if no sidecar). "subject_id": lock onto a specific face named in the sidecar (pass subject_id). "follow": switch crop between active speakers across the clip using the sidecar's active_speaker_timeline (per-segment encode + concat). "manual": caller specifies the subject (pass subject_box or subject_x_offset). See /.well-known/weftly-subjects-v1.schema.json. auto/subject_id/follow fall back to center if detection fails — the paid job always delivers a clip.
subject_id	string	optional	Required when subject="subject_id". Subject id from the parent's subjects-sidecar (e.g. "face_0").
subject_box	object	optional	For subject="manual" — bounding box of the subject in source pixels. Crop centers on the box center.
t_ref	number	optional	For subject="manual" with subject_box — source-seconds timestamp the box applies to. Informational in v1.
subject_x_offset	number	optional	For subject="manual" — direct crop x-offset in source pixels (alternative to subject_box).
job_id	string	optional	Job ID returned from a previous extract_vertical_clip call. Include along with payment_credential to confirm payment and trigger processing. Also include alone to recover the current state.
payment_credential	string	optional	MPP payment credential (full Authorization header value, e.g. "Payment eyJ..."). extract_vertical_clip accepts Tempo USDC and Stripe SPT — see the challenge's WWW-Authenticate header or /.well-known/mpp.json for the supported methods. Include with job_id after paying the challenge to start processing.

Raw schema

{
  "type": "object",
  "properties": {
    "source_job_id": {
      "description": "Job ID of any prior video job (find_clips, summarize, or video transcribe). Possessing this id is the capability — extract_vertical_clip is not session-bound, so a user can come back from a different session within the parent's TTL and still extract. Required on the first call.",
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    },
    "start": {
      "description": "Source-relative start time in seconds. Required on the first call.",
      "type": "number",
      "minimum": 0
    },
    "end": {
      "description": "Source-relative end time in seconds (must be > start; end - start must be at least 1s, and no more than the selected profile's cap — 240s for tiktok-primary/tiktok-primary-720p, 180s for instagram-reels, 60s for instagram-stories). Required on the first call.",
      "type": "number",
      "minimum": 0
    },
    "title": {
      "description": "Optional title for the assembled clip. Surfaces in get_job_status and download filenames; doesn't affect the cut itself.",
      "type": "string",
      "maxLength": 200
    },
    "profile": {
      "description": "Optional encoding profile. Default: tiktok-primary (1080×1920 H.264 fast preset, CRF 22, 6 Mbps cap). tiktok-primary-720p: 720×1280, CBR 3 Mbps — half-resolution mobile-optimized, ~40% faster wall time. instagram-reels: 1080×1920 H.264 slow preset, CBR 4 Mbps. instagram-stories: same encode shape as instagram-reels. All four apply loudness normalization to -14 LUFS / -1.5 dBTP.",
      "type": "string",
      "enum": [
        "tiktok-primary",
        "tiktok-primary-720p",
        "instagram-reels",
        "instagram-stories"
      ]
    },
    "subject": {
      "description": "Optional reframing strategy. Default: \"center\" (hardcoded center crop, today's behavior). \"auto\": lock onto the longest-tracked face from the parent find_clips job's subjects-sidecar (or run inline detection if no sidecar). \"subject_id\": lock onto a specific face named in the sidecar (pass subject_id). \"follow\": switch crop between active speakers across the clip using the sidecar's active_speaker_timeline (per-segment encode + concat). \"manual\": caller specifies the subject (pass subject_box or subject_x_offset). See /.well-known/weftly-subjects-v1.schema.json. auto/subject_id/follow fall back to center if detection fails — the paid job always delivers a clip.",
      "type": "string",
      "enum": [
        "center",
        "manual",
        "auto",
        "subject_id",
        "follow"
      ]
    },
    "subject_id": {
      "description": "Required when subject=\"subject_id\". Subject id from the parent's subjects-sidecar (e.g. \"face_0\").",
      "type": "string",
      "maxLength": 64
    },
    "subject_box": {
      "description": "For subject=\"manual\" — bounding box of the subject in source pixels. Crop centers on the box center.",
      "type": "object",
      "properties": {
        "x": {
          "type": "number",
          "minimum": 0
        },
        "y": {
          "type": "number",
          "minimum": 0
        },
        "w": {
          "type": "number",
          "exclusiveMinimum": 0
        },
        "h": {
          "type": "number",
          "exclusiveMinimum": 0
        }
      },
      "required": [
        "x",
        "y",
        "w",
        "h"
      ],
      "additionalProperties": false
    },
    "t_ref": {
      "description": "For subject=\"manual\" with subject_box — source-seconds timestamp the box applies to. Informational in v1.",
      "type": "number",
      "minimum": 0
    },
    "subject_x_offset": {
      "description": "For subject=\"manual\" — direct crop x-offset in source pixels (alternative to subject_box).",
      "type": "number",
      "minimum": 0
    },
    "job_id": {
      "description": "Job ID returned from a previous extract_vertical_clip call. Include along with payment_credential to confirm payment and trigger processing. Also include alone to recover the current state.",
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    },
    "payment_credential": {
      "description": "MPP payment credential (full Authorization header value, e.g. \"Payment eyJ...\"). extract_vertical_clip accepts Tempo USDC and Stripe SPT — see the challenge's WWW-Authenticate header or /.well-known/mpp.json for the supported methods. Include with job_id after paying the challenge to start processing.",
      "type": "string"
    }
  },
  "additionalProperties": false
}

clips_vertical

Batch-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.

Parameters6

source_job_id	string	optional	Job ID of a prior find_clips job. Possessing this id is the capability — clips_vertical is not session-bound, so a user can come back from a different session within the parent's TTL and still cut. Required on the first call.
clips	array	optional	Your own chosen clips (1-5) from source_job_id's clip-candidates output — nothing is auto-selected. Each is cut as a separate vertical clip; the batch is charged N × the per-clip price as one payment covering the whole set, not one charge per clip. Total duration across all clips is capped. Required on the first call.
profile	string	optional	Optional encoding profile applied to every clip in the batch. Default: tiktok-primary (1080×1920 H.264 fast preset, CRF 22, 6 Mbps cap). tiktok-primary-720p: 720×1280, CBR 3 Mbps. instagram-reels: 1080×1920 H.264 slow preset, CBR 4 Mbps. instagram-stories: same encode shape as instagram-reels. Also sets each clip's max duration (240s/180s/60s). All four apply loudness normalization to -14 LUFS / -1.5 dBTP.
subject	string	optional	Optional reframing strategy applied to every clip in the batch. Default: "follow" — cuts between active-speaker framings across each clip, the mode that makes multi-speaker interview clips usable. "auto": one detected framing for the whole clip. "center": fixed centre crop, no detection. "subject_id" and "manual" are not supported here — they need per-clip data a batch call cannot supply; use extract_vertical_clip directly for those.
job_id	string	optional	Job ID returned from a previous clips_vertical call. Include along with payment_credential to confirm payment and trigger processing. Also include alone to recover the current state.
payment_credential	string	optional	MPP payment credential (full Authorization header value, e.g. "Payment eyJ..."). clips_vertical accepts Tempo USDC and Stripe SPT — see the challenge's WWW-Authenticate header or /.well-known/mpp.json for the supported methods. Include with job_id after paying the challenge to start processing.

Raw schema

{
  "type": "object",
  "properties": {
    "source_job_id": {
      "description": "Job ID of a prior find_clips job. Possessing this id is the capability — clips_vertical is not session-bound, so a user can come back from a different session within the parent's TTL and still cut. Required on the first call.",
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    },
    "clips": {
      "description": "Your own chosen clips (1-5) from source_job_id's clip-candidates output — nothing is auto-selected. Each is cut as a separate vertical clip; the batch is charged N × the per-clip price as one payment covering the whole set, not one charge per clip. Total duration across all clips is capped. Required on the first call.",
      "minItems": 1,
      "maxItems": 5,
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "start": {
            "type": "number",
            "minimum": 0,
            "description": "Source-relative start time in seconds."
          },
          "end": {
            "type": "number",
            "minimum": 0,
            "description": "Source-relative end time in seconds. Must be > start."
          },
          "title": {
            "description": "Optional title for this clip; surfaces in the clips-manifest output and download filenames.",
            "type": "string",
            "maxLength": 200
          }
        },
        "required": [
          "start",
          "end"
        ],
        "additionalProperties": false
      }
    },
    "profile": {
      "description": "Optional encoding profile applied to every clip in the batch. Default: tiktok-primary (1080×1920 H.264 fast preset, CRF 22, 6 Mbps cap). tiktok-primary-720p: 720×1280, CBR 3 Mbps. instagram-reels: 1080×1920 H.264 slow preset, CBR 4 Mbps. instagram-stories: same encode shape as instagram-reels. Also sets each clip's max duration (240s/180s/60s). All four apply loudness normalization to -14 LUFS / -1.5 dBTP.",
      "type": "string",
      "enum": [
        "tiktok-primary",
        "tiktok-primary-720p",
        "instagram-reels",
        "instagram-stories"
      ]
    },
    "subject": {
      "description": "Optional reframing strategy applied to every clip in the batch. Default: \"follow\" — cuts between active-speaker framings across each clip, the mode that makes multi-speaker interview clips usable. \"auto\": one detected framing for the whole clip. \"center\": fixed centre crop, no detection. \"subject_id\" and \"manual\" are not supported here — they need per-clip data a batch call cannot supply; use extract_vertical_clip directly for those.",
      "type": "string",
      "enum": [
        "follow",
        "auto",
        "center"
      ]
    },
    "job_id": {
      "description": "Job ID returned from a previous clips_vertical call. Include along with payment_credential to confirm payment and trigger processing. Also include alone to recover the current state.",
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    },
    "payment_credential": {
      "description": "MPP payment credential (full Authorization header value, e.g. \"Payment eyJ...\"). clips_vertical accepts Tempo USDC and Stripe SPT — see the challenge's WWW-Authenticate header or /.well-known/mpp.json for the supported methods. Include with job_id after paying the challenge to start processing.",
      "type": "string"
    }
  },
  "additionalProperties": false
}

clips_horizontal

Batch-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.

Parameters4

source_job_id	string	optional	Job ID of a prior find_clips job. Possessing this id is the capability — clips_horizontal is not session-bound, so a user can come back from a different session within the parent's TTL and still cut. Required on the first call.
clips	array	optional	Your own chosen clips (1-5) from source_job_id's clip-candidates output — nothing is auto-selected. Each is cut as a SEPARATE horizontal file; the batch is charged N × the per-clip price as one payment covering the whole set, not one charge per clip. Total duration across all clips is capped. Required on the first call.
job_id	string	optional	Job ID returned from a previous clips_horizontal call. Include along with payment_credential to confirm payment and trigger processing. Also include alone to recover the current state.
payment_credential	string	optional	MPP payment credential (full Authorization header value, e.g. "Payment eyJ..."). clips_horizontal accepts Tempo USDC and Stripe SPT — see the challenge's WWW-Authenticate header or /.well-known/mpp.json for the supported methods. Include with job_id after paying the challenge to start processing.

Raw schema

{
  "type": "object",
  "properties": {
    "source_job_id": {
      "description": "Job ID of a prior find_clips job. Possessing this id is the capability — clips_horizontal is not session-bound, so a user can come back from a different session within the parent's TTL and still cut. Required on the first call.",
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    },
    "clips": {
      "description": "Your own chosen clips (1-5) from source_job_id's clip-candidates output — nothing is auto-selected. Each is cut as a SEPARATE horizontal file; the batch is charged N × the per-clip price as one payment covering the whole set, not one charge per clip. Total duration across all clips is capped. Required on the first call.",
      "minItems": 1,
      "maxItems": 5,
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "start": {
            "type": "number",
            "minimum": 0,
            "description": "Source-relative start time in seconds."
          },
          "end": {
            "type": "number",
            "minimum": 0,
            "description": "Source-relative end time in seconds. Must be > start."
          },
          "title": {
            "description": "Optional title for this clip; surfaces in the clips-manifest output and download filenames.",
            "type": "string",
            "maxLength": 200
          }
        },
        "required": [
          "start",
          "end"
        ],
        "additionalProperties": false
      }
    },
    "job_id": {
      "description": "Job ID returned from a previous clips_horizontal call. Include along with payment_credential to confirm payment and trigger processing. Also include alone to recover the current state.",
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    },
    "payment_credential": {
      "description": "MPP payment credential (full Authorization header value, e.g. \"Payment eyJ...\"). clips_horizontal accepts Tempo USDC and Stripe SPT — see the challenge's WWW-Authenticate header or /.well-known/mpp.json for the supported methods. Include with job_id after paying the challenge to start processing.",
      "type": "string"
    }
  },
  "additionalProperties": false
}

complete_upload

Confirm 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.

Parameters1

job_id

string

required

The job_id returned from a previous transcribe or summarize call.

Raw schema

{
  "type": "object",
  "properties": {
    "job_id": {
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
      "description": "The job_id returned from a previous transcribe or summarize call."
    }
  },
  "required": [
    "job_id"
  ],
  "additionalProperties": false
}

get_job_status

Check 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").

Parameters2

job_id	string	required	The job_id returned from a previous transcribe or summarize call.
format	string	optional	When the job is completed, return the transcript inline in this format instead of only a download URL. Options: "srt" (SubRip with timestamps), "txt" (plain text — no timestamps), "vtt" (WebVTT), "json" (v1, segments only), "words" (v2, segments + per-word timestamps matching /.well-known/weftly-transcript-v2.schema.json). Omit for download URLs only.

Raw schema

{
  "type": "object",
  "properties": {
    "job_id": {
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
      "description": "The job_id returned from a previous transcribe or summarize call."
    },
    "format": {
      "description": "When the job is completed, return the transcript inline in this format instead of only a download URL. Options: \"srt\" (SubRip with timestamps), \"txt\" (plain text — no timestamps), \"vtt\" (WebVTT), \"json\" (v1, segments only), \"words\" (v2, segments + per-word timestamps matching /.well-known/weftly-transcript-v2.schema.json). Omit for download URLs only.",
      "type": "string",
      "enum": [
        "srt",
        "txt",
        "vtt",
        "json",
        "words"
      ]
    }
  },
  "required": [
    "job_id"
  ],
  "additionalProperties": false
}

mpp_smoke_test

Smoke-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.

Parameters1

payment_credential

string

optional

MPP payment credential (full Authorization header value, e.g. "Payment eyJ...") obtained by paying the challenge returned from the first call. Include to verify payment and receive {paid: true}. Omit on the first call.

Raw schema

{
  "type": "object",
  "properties": {
    "payment_credential": {
      "description": "MPP payment credential (full Authorization header value, e.g. \"Payment eyJ...\") obtained by paying the challenge returned from the first call. Include to verify payment and receive {paid: true}. Omit on the first call.",
      "type": "string"
    }
  },
  "additionalProperties": false
}

publish_to_youtube

Publish 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).

Parameters7

session_token	string	required	Session token from create_session, create_transcript, or create_summary
access_token	string	required	YouTube OAuth2 access token — the caller is responsible for obtaining this via Google OAuth
refresh_token	string	optional	YouTube OAuth2 refresh token — if provided, the Workflow will refresh the access token automatically before uploading
source_job_id	string	required	Job ID of an existing transcribe or summarize job in this session whose video to publish. The Workflow will auto-generate captions if no transcript is found.
title	string	required	YouTube video title (max 100 characters)
visibility	string	required	YouTube video visibility: "private" (default), "unlisted", or "public"
description	string	optional	YouTube video description (max 5000 characters)

Raw schema

{
  "type": "object",
  "properties": {
    "session_token": {
      "type": "string",
      "description": "Session token from create_session, create_transcript, or create_summary"
    },
    "access_token": {
      "type": "string",
      "description": "YouTube OAuth2 access token — the caller is responsible for obtaining this via Google OAuth"
    },
    "refresh_token": {
      "description": "YouTube OAuth2 refresh token — if provided, the Workflow will refresh the access token automatically before uploading",
      "type": "string"
    },
    "source_job_id": {
      "type": "string",
      "description": "Job ID of an existing transcribe or summarize job in this session whose video to publish. The Workflow will auto-generate captions if no transcript is found."
    },
    "title": {
      "type": "string",
      "maxLength": 100,
      "description": "YouTube video title (max 100 characters)"
    },
    "visibility": {
      "default": "private",
      "description": "YouTube video visibility: \"private\" (default), \"unlisted\", or \"public\"",
      "type": "string",
      "enum": [
        "private",
        "unlisted",
        "public"
      ]
    },
    "description": {
      "description": "YouTube video description (max 5000 characters)",
      "type": "string",
      "maxLength": 5000
    }
  },
  "required": [
    "session_token",
    "access_token",
    "source_job_id",
    "title",
    "visibility"
  ],
  "additionalProperties": false
}

trigger_youtube_publish

Start 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.

Parameters2

session_token	string	required	Session token
job_id	string	required	Job ID returned by publish_to_youtube

Raw schema

{
  "type": "object",
  "properties": {
    "session_token": {
      "type": "string",
      "description": "Session token"
    },
    "job_id": {
      "type": "string",
      "description": "Job ID returned by publish_to_youtube"
    }
  },
  "required": [
    "session_token",
    "job_id"
  ],
  "additionalProperties": false
}

get_youtube_publish_status

Check 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.

Parameters2

session_token	string	required	Session token
job_id	string	required	Job ID returned by publish_to_youtube

Raw schema

{
  "type": "object",
  "properties": {
    "session_token": {
      "type": "string",
      "description": "Session token"
    },
    "job_id": {
      "type": "string",
      "description": "Job ID returned by publish_to_youtube"
    }
  },
  "required": [
    "session_token",
    "job_id"
  ],
  "additionalProperties": false
}

Install

Tools (13)

transcribesummarizefind_clipsextract_clipextract_vertical_clipclips_verticalclips_horizontalcomplete_upload

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://api.weftly.ai/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "weftly": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://api.weftly.ai/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

ai.weftly/weftly (MCP Server)

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

transcribe

summarize

find_clips

extract_clip

extract_vertical_clip

clips_vertical

clips_horizontal

complete_upload

get_job_status

mpp_smoke_test

publish_to_youtube

trigger_youtube_publish

get_youtube_publish_status

Install

Remote endpoint

Related servers