"Maintaining Consistent Behavior in System Prompts" matching MCP connectors:

The CNAPS.ai MCP Server lets Claude build and run AI image, video, and text pipelines mid-conversation — no dashboard, no manual node-wiring. Describe a task in plain language (e.g. "upscale this photo 4x") and Claude selects the right model(s), wires a pipeline, and runs it.

One tool surface for music, image, video, and audio generation across Suno, Grok Imagine, Seedance, Kling, Hailuo, Wan, VEO, Ideogram, and GPT Image 2. Generate, edit, upscale, reframe, and master through one credit pool. Connect in one click with OAuth, no API key required.

Deepfake detection, media intelligence, and invisible watermarking for audio, image, and video via the Resemble AI API, plus docs tools. Remote MCP server (Streamable HTTP) — also published in the official MCP registry as io.github.resemble-ai/resemble-mcp.

Generate a custom QR code in PNG or SVG format.

Opens, inspects, and renders DXF/CAD drawings for AI agents: describe_dxf returns structured facts (layers with actual drawn colors, units, bounds, text content) and render_dxf returns PNG images. On MCP Apps hosts like ChatGPT and Claude, view_dxf opens an interactive in-chat viewer with pan, zoom, and layer toggles.

x402 image tools (USDC/Base): remove_background/upscale $0.02, resize/optimize $0.005; URL in/out

Generate logos, social posts, app screenshots, comic panels & visual-novel assets from prompts.

Arabic-first AI creative platform for Egyptian and Arab businesses. Generate social media designs, write marketing copy in Egyptian dialect, build content calendars, produce Sora-2 videos, AI photoshoots, music tracks, and business documents — with your brand identity automatically applied. Requires a Grow or Business subscription at vizzy.space.

Fireship-style short videos from a topic — Remotion motion graphics, word-timed captions, 1080p.

Video analysis AI: transcripts, summaries, visual scenes/shots, clips, answers in natural language.

Meepo MCP Server connects AI agents to a professional design platform. Generate Instagram posts, LinkedIn carousels, TikTok videos, brand assets, and multi-slide campaigns — all through natural language tool calls. What agents can do: Create designs (social media, marketing, brand assets) in any format/ratio Manage multiple brand profiles (colors, fonts, logos, tone of voice) Generate AI videos and UGC-style content Run Campaign AI — one prompt generates 20+ campaign concepts Schedule and auto

Transform video, audio and images, and generate media from prompts. FFmpeg, captions, models.

Vidmoat is an AI video editor built for agents. Tell the built-in AI what you want—or plug in Claude or Cursor—and it automatically cuts dead air, writes karaoke captions, removes backgrounds, and reframes your video for every platform.

Hindi, Marathi, Gujarati & English calligraphy artwork in your AI assistant, by Studio99.

Create videos with prompts, and use Rendley’s video editor to adjust anything you need.

Search, generate, and curate AI media assets with recipes and lineage in Make Effects spaces.

Search 324k icons or generate new ones in the Lucide grammar - grammar-locked lint+critique+repair

The AI influencer MCP for Claude: research trends and write reel scripts, render in the app.

FFmpeg Micro MCP Server. Transcode videos from n8n or Make using FFmpeg in the cloud. Code+Docs: https://github.com/javidjamae/ffmpeg-micro-mcp/

Browse, search, upload, tag, transfer, and delete images in your Raster libraries over MCP.