"Understanding Persistent Memory in Cursor Functionality" 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.

AetherWave StudioA

com.aetherwavestudio.mcp

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.

Script in, finished 1080p narrated video out. Pay per call in USDC via x402.

Any video URL to LLM-ready transcript. ASR built in, no captions needed. TikTok, X, TED and more.

Generate a custom QR code in PNG or SVG format.

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

John's EssentialsBOAuth

com.johnsessentials

144 deterministic file tools: PDF, image, media, convert, analyze. Connect in one click (OAuth).

reapOAuth

video.reap.mcp

The Reap MCP server connects your AI agent directly to your Reap workspace. Once connected, your agent can run the full pipeline for you — upload a video, generate clips, add captions, reframe, dub, transcribe, and publish to social platforms — all from inside your chat. Works with Cursor, Claude Code, VS Code, GitHub Copilot, Codex, Gemini CLI, and any other MCP-compatible agent.

Generate, edit, and render videos, images, and audio via the Shotstack video editing API. Compose Edit JSON timelines, use saved templates, and track render jobs from Claude, Cursor, ChatGPT, and other AI tools.

Official Zvid MCP server: render videos and images from JSON and manage templates, projects, webhooks and credits from any MCP client — Claude, Cursor, Codex, n8n — through the Zvid REST API.

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

video-assistant-mcpOAuth

com.valossa

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

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.

Generate images, video, audio and 3D with FlowNode; results land in your asset library.

Screenshots, PDFs, QR codes, clips and template renders with a normal OAuth sign-in.

FFmpeg APIOAuth

com.ffmpeg-api

Run FFmpeg and FFprobe in the cloud: convert, compress, trim and analyze video and audio.

GoVideoOAuth via extension

stream.govideo

Drop in a video, get a link that plays anywhere — plus chapters, player styling and analytics.

AvatarFactoryOAuth via extension

io.avatarfactory

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

3D avatars, embeds, glTF tools, agent memory, and on-chain agent identity from three.ws.

xSkill AI

io.github.hexiaochun

AI content generation with 50+ models: image, video, TTS, voice cloning, and more.