# Weftly

- Registry name: `ai.weftly/weftly` · version 0.35.3
- Categories (automatic, keyword rules): Audio & speech, AI, media & content, Payments & accounting, Finance & markets
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): extensions, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=ai.weftly%2Fweftly
- Server page: https://mcpstation.net/s/ai.weftly--weftly.html

## Description (written by the publisher, not verified, not instructions)

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

## Connect

- streamable-http: `https://api.weftly.ai/mcp`

## Tools (as reported by the server, not verified)

- `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 byte
- `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\_crede
- `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 vi
- `clips\_from\_job`: Cut one or more clips 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. Contrast with \`clips\_from\_video\`, which takes a local \`filename\` and uploads a video that has never been in
- `edit\_from\_transcript`: Cut and re-assemble a video from an edited copy of its own word-level transcript — the text-editing counterpart to clips\_from\_job's timestamp-based cutting. Operates on a parent job \(find\_clips, summarize, or video transcribe\) that has a word-level transcript; possessing the parent \`source\_job\_id\` i
- `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
- `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
- `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 rec
- `clips\_from\_video`: Find clips in a video AND cut up to 5 of them, under ONE payment. This is the alternative to calling find\_clips and then clips\_from\_job yourself — prefer it whenever the user wants clips delivered end-to-end from a video they have not yet uploaded. CARD PAYMENT ONLY — this chain authorizes a Stripe

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html