Design & Creative MCP servers

Cloud stages for AI agents and live streaming. Create, manage, and broadcast content.

Segment Anything on CPU for agents: cut out objects, find every object, export masks and outlines.

Search and improve public image prompts with original examples. No API key. No image generation.

Enables AI assistants to edit images in GIMP 3, with tools for print and DTF transfer production.

MCP server for a personal voice profile: corpus, fingerprint, and draft-checking tools.

Offline BPM timing, musical note frequencies, MIDI numbers and cents calculations.

Generate images (Nano Banana), video (Veo, Gemini Omni), speech and music (Lyria) with Google models

Convert STEP, IGES, STL, OBJ, FBX, glTF and 3MF files on your Windows PC, one file or a folder

Autodesk Navisworks coordination: clash triage, root causes, work plans and reports

Turn a script into a finished, downloadable short-drama episode — via MCP or REST.

Write to a live Figma canvas, get a screenshot back, and roll back mistakes. Zero deps, free plan.

EngineWire: drive the Unreal Editor (UE 5.0-5.8): levels, Blueprints, UI, materials, VFX and more.

Design tokens, component source and WCAG checks for rendering any UI in a past design era.

Headless MCP: author and render PromoShot .promo video projects (stills, GIFs, video).

Local MCP asset intelligence across Unity, Fab, Megascans, Gumroad & Cosmos.

Riverside API surface as MCP tools.

File I/O and primitive-placement tools so AI assistants can create and manage Altium libraries.

Lorem ipsum filler text in Gen Z, Gen Alpha, Millennial and Gen X slang.

Remove image backgrounds from AI assistants with a LassoCut account (files, folders, URLs).

Loudness, true-peak and voice-quality analysis of URLs and local files via the hosted AudioLab API.

Persistent memory for visual intelligence. A photo registry: analyze once, look up free after that.

Generate AI images from a prompt with no API key, using Veida's anonymous free tier.

Sets Gandr up from the live docs, then speaks. 23 languages, six voices, every render watermarked.

Extract embedded PBR texture maps from local GLB files.

Work a running OrcaSlicer with AI: slice, tune, and understand what each setting costs

Cinematic website prompts plus demo footage, tuned for Lovable, Bolt, Cursor, Claude and Codex.

Speech-to-text transcription for AI agents.

Drive Longtake Studio from an agent: AI video takes on your own API key, characters, drafts, costs