Design & Media MCP Servers for DeepSeek Harness

Talk through your working day as a short interview, then film it as a build-in-public episode.

Finished TikTok/Instagram carousels from a topic, photos or video. Edit any layer, export PSD/SVG.

Read-only canon of design and copy rules for AI agents to audit generated UI, served as resources.

Develop a film from first idea to animatic: story bible, screenplay and storyboard in one place.

Generate AI videos, images and audio on Veevid with Veo 3.1, Kling 3.0, Seedance 2.5 and more.

Create AI videos from photos with templates, track jobs, and download results using Vellm points.

AI video studio on Velos: product videos, UGC ads, product photos, posting and autopilot.

Remove video backgrounds with OAuth, account credits and transparent WebM downloads.

Read videos like images: index once locally, query the text layer, fetch frames on demand.

AI video upscaler: enhance videos to 1080p, 2K or 4K and track upscaling tasks.

AI transcription API: turn voice memos, meetings and audio URLs into text and SRT subtitles.

Transcribe, subtitle, dub and lip-sync media; create speech, voices, images and thumbnails.

Create rythmo bands for dubbing: upload a video, transcribe, edit lines, style, and export.

AI creative studio for your assistant: ad templates, video, image and audio, priced before each run.

Read visual design reviews from live web pages: comments, CSS selectors, styles, console errors.

Logo, colors, typefaces, tone of voice and CSS theme of any brand, read from its own website.

Create songs from prompts or lyrics, check credits, and access your private library with OAuth.

Make short branded ad and social videos from a product link, script or idea, in your chat.

Turn a website URL into a launch video with voice-over. Edit by chat, export MP4.

Private on-device speech to text: transcribe audio files and search your Yap dictations. No upload.

Make micro dramas and anime episodes from an idea, with the same characters in every shot.