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.
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 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.
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.
Exposes ocrmypdf as a single tool for OCR-ing scanned PDFs, with automatic PATH handling for Tesseract and Ghostscript on Windows to ensure compatibility with Claude Desktop.
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 drive a running Adobe After Effects (~270 undo-safe operations). Works with every UI language Adobe ships and sees the frame: draws Object Matte on what it sees (lassos, ⊕/⊖ points, a preview of gaps and people) and syncs AI-generated layers with the plate frame by frame. A large skills library, built for AI and generative features: Roto Brush, Object Matte, Content-Aware Fill.
Extends Beeper Desktop's built-in MCP server with file and conversation tools: downloading message attachments to disk, sending local files with captions, searching contacts across accounts, starting new direct chats, and deleting messages. It runs alongside the official server, letting assistants handle media and reach people you've never messaged.
Lets AI agents drive a running Adobe Premiere Pro (~440 verified operations). Works with every UI language Adobe ships and sees the frame: draws Object Masks on what it sees (a click for a person, a lasso for a face; ⊕/⊖, tracking) and places speed keyframes on the timeline by sight. A large skills library, built for Generative Extend, Generative Media, Object Mask, Enhance Speech.
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.
A local MCP server that enables Claude to edit videos on your machine using ffmpeg, with tools for trimming, converting, compressing, creating GIFs, and more.
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 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.
A professional video format conversion tool based on MCP protocol that supports multiple formats, batch processing, and quality control for video files.
Generates realistic human face images that don't represent real people, offering various output shapes, configurable dimensions, and batch generation capabilities.
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
A stdio MCP server for DaVinci Resolve on macOS, enabling project control, timeline navigation, frame capture, grade application, and validation through the official Resolve scripting API.
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.
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.
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.
A MCP server for video multimodal understanding based on Alibaba Cloud DashScope, enabling video content analysis, summarization, scene recognition, and custom analysis.
Enables AI agents to edit OpenShot 4.0 video projects by importing media, detecting a music beat grid, placing clips on the grid, and saving the project.
Enables MCP-compatible clients to control Blender for modeling, materials, animation, physics, rendering, scene inspection, documentation search, and asset/generation service integration. It exposes a stdio endpoint with many Blender operations for creating and editing 3D content.
Enables conversion of files among 44 document, spreadsheet, image, ebook, and subtitle formats by forwarding base64 or public HTTPS URL inputs to a hosted conversion service and returning inline or downloadable outputs.
Connects MCP-compatible clients to a live Blender scene for AI-assisted 3D workflows, enabling inspection and controlled operations on objects, materials, cameras, lights, render settings, animation, UVs, Geometry Nodes, imports, exports, and Python execution.
Enables AI assistants and agents to edit existing videos with plain-language instructions and reference photos, including removing people or objects, changing outfits, backgrounds, products, faces, styles, or adding effects while preserving framing and audio. Supports uploading media, quoting and starting edits, checking job status, and retrieving private result links.
A self-hosted, read-only MCP service that searches public YouTube and Bilibili videos and produces compact evidence packages with verified metadata, timestamped captions or ASR, frames, OCR, and contact sheets for ChatGPT/Codex analysis.
Enables efficient analysis of recorded meetings by transcribing audio, extracting only non-people frames (e.g., slides), and associating them with timestamps for compact LLM input.