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.
Enables MCP-compatible agents to access KaiRouter's video generation API, providing tools to list available video models, generate videos (text-to-video or image-to-video) asynchronously, check job status, and list recent jobs.
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 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.
A mock-first MCP server for audio generation that creates placeholder WAV files locally, enabling development and testing of audio workflows without APIs or costs.
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 assistants to open, inspect, and edit StykAnimate and Pivot stick figure animation projects — reading rigs and timelines, evaluating poses at any frame, and transforming figures, keyframes, layers, and colors without a browser or GPU. Changes are undoable and projects can be saved or exported back to StykAnimate or Pivot formats.
Enables AI assistants to inspect and safely control OBS Studio over obs-websocket v5, exposing scenes, inputs, filters, outputs and video settings as read and write tools that default to dry runs and refuse changes while live unless explicitly confirmed. It also provides Source Record and IRL readiness checks, a BRB auto-switcher, and a scene timeline log for cutting clips from VODs.
Enables an AI agent to drive a live Blender session, building, sculpting, measuring, checking, rigging, lighting, rendering and exporting 3D models through safe operations in world units. Every geometry-changing call reports achieved dimensions, open edges and failures as numbers and review images, so modelling mistakes become visible instead of silent.
Enables MCP clients to place client and Frame.io comments as Final Cut Pro to-do markers, compare FCPXML exports to see clip and transition changes and which notes a recut touched, and attribute timeline edits to journaled agent tool calls.
Lets AI assistants act as a sound engineer for a Behringer XR18 digital mixer, connecting over OSC/UDP to read status, adjust faders/EQ/gains/mutes, manage monitor mixes, and save or undo changes with safety guards.
Enables AI assistants to transcribe audio files from URLs or local paths using AssemblyAI's services, with support for speaker diarization, language detection, and asynchronous job management through a standardized MCP interface.
A unified MCP server for video generation that intelligently routes requests to HeyGen (for avatar/presenter videos) or Google Veo (for creative/cinematic content).
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.
Enables an assistant to control a logged-in desktop or mobile player through the official cloud API, including pause/resume, skip, seek, volume changes, playing links or playlist items, and reading playback status.
Enables AI assistants to control MIDI devices and synthesizers through WebMidi.js integration. Provides tools for sending notes, control changes, creating virtual ports, and executing complex musical sequences.
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 Claude to edit Adobe Premiere Pro timelines through natural language, with roughly 150 tools for cutting, trimming, speed changes, effects, keyframes, transitions, titles, captions, audio, markers and exports. It can also render frames so edits can be visually verified, and ships with a skill encoding a working order and rules learned from real projects.
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.
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.
Enables supported local AI clients to control a visible desktop presence through bounded presentation tools such as animations, window control, and short local speech over a loopback endpoint, without granting decision or execution authority.
Enables AI video dubbing from any MCP-capable agent: upload a video or provide a URL, submit a dubbing job, poll progress, and download the finished MP4.
Enables AI-assisted inspection and editing of Spine 4.3 animation projects, including generating simple motion drafts, adjusting keyframes per track, previewing results, and importing and validating changes through the official CLI. It also supports low-context tool sets for animation workflows.
Enables AI assistants to inspect and edit an Ableton Live set in real time, including tracks, devices, parameters, clips, MIDI, and undo-safe changes, with guardrails such as all-or-nothing validation and optional read-only mode.
Turns a YouTube video or allowlisted local video into a timestamped transcript, chronological timeline, and retrievable image resources for transparent media preprocessing.
Converts animated GIFs, WebP, APNG, or MP4 files into a single labelled contact sheet with sampled frame timestamps, enabling agents to perceive motion over time instead of a single still frame. It returns the contact sheet image plus a JSON summary of frame count, timestamps, and grid size for time-aware reasoning.
Enables AI assistants to watch YouTube videos by extracting frames at scene changes and visual references, pairing each frame with the exact words spoken at that timestamp. Provides dense frame-transcript interleaving for any model.
Enables AI clients to edit Premiere Pro timelines through natural-language requests, including cutting clips, closing gaps, adjusting color and audio, adding captions, and exporting. It shows changes on screen by moving the playhead and selecting clips as edits are made.
Enables connecting a user's own WeChat to MCP-capable AI assistants for owner-only private messaging and media exchange, including receiving text, images, files, and upstream voice transcriptions, and sending replies, images, or files.
Enables AI assistants to turn a finished image into a hand-drawn whiteboard animation, showing the drawing in chat and providing links to save the resulting MP4 or other formats.
Enables MCP clients to drive a native macOS capture app: take screenshots and screen recordings, annotate, crop and beautify, redact likely secrets, extract text, and export or share the results. Posting and scheduling to X, uploads, deletes and share-link changes are gated behind a native approval sheet on the user's Mac.
Enables AI agents to reverse-engineer a finished video into an NLE-importable edit timeline by probing media, detecting hard cuts, assembling a seconds-anchored EditSpec, and exporting FCP7 XML, EDL, or OTIO. Also renders self-contained HTML shot-review reports and shares its workspace with a matching CLI so specs produced by an agent can be exported or reported on directly.