"Exploring Memory Persistence in DeepSeek Technology" matching MCP servers:

Enables downloading content from various social media platforms through a unified API. Provides a single tool to download media from multiple social networks using the Social Download All In One service.

Provides image understanding capabilities for MCP clients (e.g., Claude Code) by analyzing images using vision models from providers like Alibaba Cloud Bailian, OpenAI, or OpenRouter, returning detailed descriptions in Markdown format.

Enables creating real Scratch 3 projects from natural language prompts, producing editable .sb3 files with sprites, scripts, sounds, and backdrops.

Hosted multi-model AI media + chat MCP server. Generates images, video, audio, face-swaps and talking-avatars, and chats across 300+ models (Claude, GPT, Gemini, DeepSeek…) - all from one balance and one API key.

Local MCP server that adds multimodal capabilities to text-only models like Codex/DeepSeek, offering tools for image description, audio transcription, video analysis, image/video generation, and speech synthesis.

Provides advanced image analysis capabilities including object recognition, OCR text extraction, and multi-turn visual dialogues using OpenAI-compatible APIs. It supports both local files and Base64 inputs with additional features for session persistence and web-based configuration management.

Enables AI-assisted electronic music production in Ableton Live, with built-in genre theory for indie dance, tech house, melodic techno, and house music.

Enables playing and inspecting local audio files in an MCP host with an in-conversation UI showing waveform, spectrogram, and loudness metrics, while exposing playback state and metadata to the model.

Enables Claude to co-produce music in a self-hosted browser DAW by creating and editing patterns, chords, basslines and melodies, arranging and automating tracks, mixing with effects and spatial placement, analyzing and editing samples, rendering mixes with mastering feedback, and exporting MIDI and stems — all reflected live in the studio.

Enables MCP clients to run project-scoped video editing workflows: propose and approve editing strategies, apply validated plans, review immutable versions, and export final renders via FFmpeg, with durable persistence and approval gates.

Enables AI assistants to convert local videos into styled ASCII art by inspecting source metadata, previewing and visually judging rendered frames, exploring preset parameters, and exporting finished clips. Supports MP4 with audio or GIF output with trimming, speed changes, reframing, beat-synced styles, and shareable editor links, all processed locally.

为DeepSeek、Claude Desktop等AI助手提供本地视觉能力，支持图片描述和视频帧分析，数据不出机。

Enables high-quality AI image generation using MiniMax (Hailuo AI) text-to-image technology through fal.ai, supporting multiple aspect ratios, prompt optimization, and both synchronous and queue-based generation with automatic local image downloads.

Lets AI assistants render HTML animations to MP4 or GIF in 16:9, 9:16 and 1:1, preview single frames to check their own work, and finish videos with royalty-free music, AI voiceover, burned-in captions, titles and logos. It renders code frame by frame in a real browser rather than generating video from a text prompt.

Control Ableton Live using natural language via Claude Code, with music theory engine for progressions, project persistence, and song cloning.

Enables coding agents to turn explanations of code, pull requests, or concepts into narrated slide walkthroughs voiced locally with Kokoro, returning a link that starts playing in about a second while the remaining slides are still being written. Slides are grounded in real files and git history, checked for errors, and exportable as static folders with captions.

Captions video and audio files on your computer with Cuecaps: animated word-by-word captions in 10 styles, exported as a burned-in MP4, a transparent MOV/WebM overlay for Premiere, Resolve or CapCut, or SRT/VTT subtitles. Rendering runs in local headless Chrome, so the video never uploads; captioning needs a Cuecaps Creator or Pro key.

Author, validate, preview, and render motion-graphics videos from a single JSON document (Clipkit Protocol). 16 tools with in-chat PNG previews, captions, templated promos, and hand-off to a free browser editor by link.

Transcribe audio/video URLs and detect silence for cutting, with pay-per-call billing in USDC via x402, no account or API key required.

Enables AI agents to turn YouTube videos into downloadable audio files in formats like MP3, M4A, WAV, FLAC, and OGG (with optional clipping), and to retrieve existing captions as text, JSON, Markdown, SRT, or VTT. Uses your own RapidAPI key and supports job polling for longer conversions.

Enables AI assistants in MCP clients to turn long videos from YouTube, VK Video, RuTube, Dzen, Twitch, Yandex Disk, Google Drive or direct links into captioned vertical Shorts/Reels, transcripts and articles, returning links to the finished clips. It also exposes read-only modes and job quoting so clients can inspect sources and estimate credit usage before creating anything.

Claude steers live music by writing Strudel code in a browser page, and can play and control real instruments over MIDI.

FableCut is a Premiere-style non-linear video editor that runs entirely in your browser — and exposes its whole timeline as one JSON document. Edit it by hand, from the UI, or let an AI agent (Claude Code, Claude Desktop, or anything that speaks MCP/REST) cut your video for you while you watch the timeline update live.

Lets AI agents mark the images and audio they generate, as the EU AI Act's Article 50 requires: an invisible watermark (TrustMark for images, AudioSeal for audio) plus a signed C2PA manifest (Content Credentials), in one tool call. Tools: mark_file (writes .marked.png/.wav next to the original, optional visible "AI-generated" label), verify_file (watermark and C2PA signature check, by path o

Enables reading and creating projects in a local CapCut draft library through natural language — listing timelines, checking for missing media, and generating new edits from clips, with cuts automatically matched to the beat of a track. It works by cloning an existing draft as a structural template, so new projects inherit CapCut's undocumented file format.

Enables searching, downloading, and placing b-roll assets (images, stock video, etc.) onto an editor timeline in DaVinci Resolve, Premiere, or via universal formats.

Lets AI apps drive a Chrome tab to record product demo walkthroughs: the AI plans the flow, navigates, clicks and types with a smooth on-screen cursor, then stops so the recording opens in an editor. Everything runs locally over a paired, user-approved connection to the Recordful extension, with no hosting, account, or API key required.

MCP server for scanning and generating barcodes and QR codes. Enables decoding barcodes from images, generating QR codes, and creating barcodes in multiple formats.

An MCP server implementation that integrates with Minimax API to provide AI-powered image generation and text-to-speech functionality in editors like Windsurf and Cursor.

Enables LLMs to directly control, introspect, and build TouchDesigner networks in real-time through a Model Context Protocol server.