Design & Media MCP Servers for Microsoft Copilot

Hosted text-to-speech MCP server: 66 voices in 9 languages, long-form narration, podcasts.

Video, audio, and image processing for AI agents: convert, transcribe, upscale - 150+ operations.

AI image editor: remove backgrounds, upscale, and edit photos by describing the change.

Cloud-hosted MCP server for Epidemic Sound

Create, edit and organize hand-drawn diagrams (flowcharts, ER, architecture) from any AI agent.

Real 3D-print slicing, quoting, DFM, orientation & material/settings advisors. Free personal tier.

Convert, probe, and split video into frames — real FFmpeg, paid per job with x402 on Base.

Verbatim transcription of public video/audio URLs to clean text, SRT, and timestamped records.

Parse a Figma file URL. Path discarded.

AI film studio: shoot video, images and sound, review takes, audit scripts, quote before you shoot.

AI film lab for filmmakers: generate and review images/clips with input provenance, cost preflight

Feedback layer for video. Reviewers talk through feedback; agents read it as structured comments.

Cloudflare Workers MCP server: font-metadata

Search and license 54,000+ drone, aerial, and ocean clips, mostly 4K, from filmmaker Phil Maher.

Start with classify_media_route to route long or oversized audio/video by size or duration.

Generate images, video, music, voice and 3D through one API. 30 tools, 200+ models.

Create long-form YouTube videos end to end: script, storyboard, voiceover, final MP4.

Film stills from 5,489 films, searchable by lighting, lens character, shot size, colour and mood.

UX research platform: manage studies, browse templates, read responses and analytics.

Build websites that look designed, not generated. Fudge gives AI real websites to study.

No longer listed separately (still callable): public provenance evidence for art collections.