Enables AI agents to perform local video, audio, and file operations inside an isolated workspace, including cutting/concat videos, extracting audio, transcribing, and managing files, with typed responses and background job support.
MCP server that bridges Ableton Live with AI models, enabling real-time project inspection and control such as track overview, device parameters, and audio analysis.
Enables AI assistants to inspect and organize Adobe Premiere Pro projects, edit timelines with frame-accurate cuts and trims, animate motion and opacity keyframes, and trigger exports through natural language.
Enables AI assistants to programmatically inspect projects, create compositions and layers, apply effects, animate properties, and manage render jobs in Adobe After Effects through natural language.
Enables WorkBuddy and other MCP-compatible clients to generate images and videos from natural-language prompts through Agnes AI, returning online URLs and locally saved files.
Windows-optimized MCP server that enables control of Blender 4.0+ through 21+ tools for scene management, object manipulation, and asset downloads from PolyHaven, Sketchfab, Hyper3D, and Hunyuan3D.
MCP server for Takes, a free, open-source Mac teleprompter and recorder for talking-head videos. It lets an AI assistant write scripts and storyboards, manage takes, make edits and draft the posts for LinkedIn, X, YouTube and Shorts.
Enables MCP clients to operate local Adobe Premiere Pro projects, covering media ingest, bins, sequence and timeline editing, transitions, effects, keyframes, captions, markers, metadata, proxies, multicam, color, audio, and exports through 283 discoverable tools, 13 context resources, and 10 guided prompts. A bundled CEP panel provides the supported production bridge, with read-only connection verification and higher-level workflows for assembling product spots and motion-graphics demos.
Enables AI clients to drive local video editing projects through a CEP bridge, covering media ingest, sequence and timeline editing, effects, keyframes, captions, markers, audio, color, and exports across hundreds of discoverable tools. Ships context resources, guided prompts, and higher-level assembly workflows for agent-driven editing.
MCP server for Blender that connects to the official Blender Lab add-on, exposing 27 tools for scene manipulation, object editing, materials, rendering, and Python execution through the add-on's actual wire protocol.
Enables coding agents to inspect and manipulate video and audio through ffmpeg-backed tools for probing, trimming, cropping, resizing, extracting audio or frames, generating thumbnails, normalizing loudness, concatenating files, burning captions, and converting formats. Each operation returns concise JSON with output path, size, and verified duration or dimensions.
Enables AI assistants to control a Blender instance through MCP tools, supporting scene creation, editing, and asset exchange via HTTP and background CLI processes.
A local MCP server that bridges Logic Pro MIDI data via an AUv3 plugin, enabling reading, creating, and manipulating MIDI regions and tracks through tools like read_logic_track and create_midi_region.
MCP server that lets AI assistants control Adobe After Effects - ExtendScript execution, background rendering, and deep project/layer inspection - with first-class Arabic/RTL and multilingual support. 44 tools.
Enables Claude or any AI agent to operate Live 12 Intro end to end: creating tracks and scenes, writing and quantizing MIDI clips, loading audio onto the Arrangement timeline, setting device parameters in real units, drawing clip automation, mixing with real sidechain, and rendering or analyzing audio so the agent can check its own work. It exposes 57 tools over MCP or a local JSON socket, working within the stock Intro edition's 16-track, 16-scene limits.
Enables Claude Code and other MCP clients to control the Mac desktop video editor through its automation server, exposing the full editor for beat-synced cuts, captions, text, transitions, keyframes, audio, frame checks, and export.
Enables Claude to inspect and build compositions in an open Adobe After Effects project, animate layers and effects, preview real frames, compare against reference video side by side, measure and recreate camera moves, detect cuts and beats, and render MP4s.
Enables AI clients to drive local Premiere Pro projects end to end — project setup, media ingest, sequence and timeline editing, effects, keyframes, captions, markers, audio, color, and exports — plus local ffmpeg/Whisper compute tools. Every mutating tool verifies its own result by readback, fingerprint, or a composited program-monitor frame, refusing to claim success it cannot confirm.
Renders validated declarative scene specifications into MP4 videos inside disposable, network-disabled containers, then serves an embedded player with playback controls and diagnostics through MCP Apps. Users can iteratively revise scenes conversationally, with revision history preserved and identical renders reused per account.
Starts shared local Streamable HTTP endpoints for Premiere Pro, After Effects, and Lightroom Classic when those apps launch, letting multiple MCP clients use the open Adobe documents.
Enables Claude Code to use Alibaba Cloud Token Plan models via a local proxy that maps Anthropic-style model names to Alibaba IDs and provides missing endpoints like model discovery.
Enables an AI assistant to read and build a running TouchDesigner network, including inspecting and wiring operators, editing GLSL/DATs, mapping MIDI, importing Shadertoy/ISF shaders, publishing to Resolume over Syphon/NDI and OSC, and diagnosing silent failures.
Enables Claude to send After Effects compositions to Adobe Media Encoder for rendering with specified output paths and encoding values, then check whether the render has finished. It also supports searching and creating presets, queueing comps, and waiting on jobs with ffprobe-verified output checks.
Enables AI clients to watch and hear videos from local files or YouTube, Vimeo, and Loom links by returning timestamped key frames, a transcript, a contact sheet, and a combined timeline, with all processing done locally.
Convert HTML to PDF/PNG/WebP/PPTX slide carousels with 11 themes. For LinkedIn carousels, decks, Instagram posts, and infographics — Puppeteer-based pixel-perfect rendering.
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 an AI assistant to produce a cover of any song in a cloned voice: it fetches the track and timed lyrics from NetEase Cloud Music, swaps the vocals via the 声线 app's singing voice-change feature, and returns a finished mp3 plus synchronized lyrics. Also lists available voices and remaining credits so users can just ask for a song by name or share link.
Enables an AI assistant to inspect local video files, grade them against Instagram, TikTok, YouTube, X and LinkedIn upload specs with concrete fixes, and re-encode them into upload-ready versions via ffmpeg. Also supports comparing multiple files, scanning whole folders for footage logs, and stripping sensitive metadata — all locally without uploading footage.
Enables Claude to analyze short-form video ads by extracting frames, audio, and transcripts, providing visual contact sheets, audio profiles, and YAMNet audio-event tags via MCP tools.
Enables agents to integrate live-stream chat, speech, VTube Studio avatars, and OBS broadcast output, with centralized management of service connections, expression rules, and stage configuration through a stdio MCP service.
Enables AI agents to monitor, manage, and operate a Tdarr transcoding farm by inspecting nodes, workers, queues, libraries, plugins, and job reports, and by triggering scans, requeues, and worker actions.
MCP server that transforms cognitive state into generative music by mapping 13 epistemic vectors to Strudel live coding patterns, with mood presets and a web UI for interactive control.
Enables AI agents to inspect and manage video renders, templates, generation models, hosted assets, and ingest sources while using isolated private account profiles. It requires explicit approval for mutation operations and supports both MCP and CLI access.
Enables interaction with Volcengine's TOS (Object Storage) service through MCP protocol. Supports bucket management, object operations, pre-signed URLs, and media processing including image manipulation and video frame extraction.
Connects an MCP client to a locally installed Adobe Premiere Pro so editors can inspect projects and run structured editing operations—project creation and opening, linked audio/video insertion and trimming, cutting, SRT caption rendering, and native MP4 export—instead of navigating the UI repeatedly. Capability profiles limit access to inspection, editing, export, or filesystem authority as needed for each task.
Image Tools MCP is a Model Context Protocol (MCP) service that retrieves image dimensions and compresses images from URLs and local files using the TinyPNG API. It supports converting images to formats like webp, jpeg/jpg, and png, providing detailed information on width, height, type, and compressi
Enables AI agents and clients to discover and use 75 V5 design-automation tools for templates, images, animations, media jobs, workflows, assets, publications, webhooks, and Instant URLs, with explicit mutation approval, local previews, and isolated private workspace profiles.
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.
Enables AI agents to build channels from video and audio playlists, start, schedule, sync, stop and monitor live broadcasts across YouTube, Facebook, Twitch, LinkedIn and X, and read stream analytics afterwards. Also covers project and scene editing, media library management with upload and encode workflows, and destination validation, over a stateless streamable HTTP endpoint authenticated with a LiveReacting API key.
An MCP server that lets AI agents compress images, PDFs, video, audio, documents, and archives, writing the smaller versions back to disk via the MiCompress service.
Connects AI assistants to a Cloudinary account so users can manage named transformations, upload presets, adaptive streaming profiles, webhooks/triggers, and upload folder mappings through natural language.
Lets AI assistants control a NUX MG-30 guitar processor over USB MIDI by picking amp, cab, drive, modulation, delay and reverb models, toggling blocks, and setting knobs by name. It can also read, save, rename, back up and restore presets on the device, and apply whole tone recipes from JSON patch files.
Enables AI agents to see and control Android devices through ADB and screen mirroring, supporting screen capture, touch input, app management, UI element finding, file transfer, shell commands, clipboard access, and audio/video streaming.
Enables agents to edit short lyrics in authorized songs by uploading audio, selecting a phrase, supplying replacement words, previewing the result, and exporting the finished track through scoped tools.
A local MCP bridge that lets AI agents build and edit real TouchDesigner networks by creating and wiring operators, setting parameters and expressions, validating the network, and viewing rendered image previews to iterate on results.
Enables the automatic generation of complete Live2D models from a single photo by automating segmentation, rigging, and physics configuration. It provides a full pipeline for creating layered art meshes and motion files through a suite of specialized animation tools.
Enables local photo grading through MCP by letting a host model inspect an image, choose a color strategy, and apply OpenCV-based LUTs to produce a graded output.