"Open Collective" matching MCP servers:

An open-source agent toolkit that auto-syncs SDK versions, docs, and examples—built for seamless integration with LLMs, and AI agents ( MCP compatible).

Enables AI assistants like Claude Code to build and edit CapCut video projects locally by creating drafts, adding media and effects, and saving projects that open in CapCut desktop.

Give ChatGPT eyes and hands: explore YouTube, websites, comments and local media. Free, open-source AI research and automation toolkit.

Enables editing inside an open Premiere Pro project by reading the real timeline, applying cuts and transcript-based cleanup in place, and verifying results with rendered frames from the Program Monitor.

Enables creating, editing, reading, and converting Word, Excel, PowerPoint, PDF, and plain-text documents, including live editing of open Office documents, template-based document generation, and high-fidelity PDF/PNG rendering.

Open-source MCP server that routes tool calls to AdPanel's production gateway for brand asset management, timeline orchestration, and broadcast asset synthesis.

Exposes Open Video Guide functions to MCP clients, enabling conversion of tutorial videos into illustrated, verifiable guides with timestamps, evidence, and review states.

Enables MCP clients to interact with a local-first film watch room, supporting media scanning, AI preparation, room management, timed messages, playback state, and storyboard image retrieval.

Converts YouTube and Bilibili videos into structured knowledge articles using local transcription or subtitle extraction combined with AI-powered summarization. It supports multiple summary styles and provides tools to process URLs, track job status, and retrieve results directly within MCP-compatible agents.

Enables agents to control a browser over HTTP MCP to open pages, take screenshots, click coordinates, and record audio/video as WebM.

Enables control of Open Brush 3D painting software through natural language commands, allowing LLMs to create drawings, manipulate brushes, import 3D models, manage colors, layers, and camera settings via the Open Brush HTTP API.

Enables AI agents to perform GIMP-style image operations such as open, resize, crop, flip, rotate, blur, desaturate, text overlay, export, and batch processing via MCP tools, supporting both mock (Pillow) and live GIMP backends.

Local TypeScript MCP server for creating authorized song-practice projects for GarageBand. It enables users to create practice workspaces from MIDI, generate bar practice assets, and open projects in GarageBand.

Local AI generation for images, audio, speech, and 3D models using open source models.

Enables AI agents to control a live Blender session through MCP tools for scene and object manipulation, rendering, and PolyHaven asset downloads. It works with any OpenAI-compatible, Ollama, LM Studio, llama.cpp, or Azure LLM backend, which can be switched at runtime without restarting.

RelayGPU MCP gives AI agents access to 80+ open and closed AI models for text, image, video, audio and embeddings. Agents can discover models, check pricing, generate content and run workflows, with new models added to the catalogue regularly.

An MCP server that masters audio with a professional signal chain using ffmpeg, enabling loudness analysis, vocal-over-beat mixing, full mastering to target LUFS, and Dolby codec export.

Optimize, convert and compare images locally with the same engines as cwebp, cjpeg, oxipng, avifenc and cjxl: WebP, AVIF, JPEG XL, JPEG and PNG. Analyze an image, pick the best format at the same perceived quality (SSIMULACRA 2), measure the loss, crop, resize and convert whole folders. Always writes new files, never overwrites or deletes. Free and open source (GPL-3.0).

Open-source screen recorder and video editor that coding agents drive over stdio: record, edit, export demo videos and add shader effects.

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 MCP clients to create, edit, preview, validate, save, and export voxel models, either on files or by live-editing the scene open in a running voxel editor. Provides drawing primitives, region recoloring, layer management, undo, PNG previews, and exports to formats such as .gox, .vox, OBJ, and glTF.

Open-source MCP server for AI image and video creation, enabling prompt library search, prompt enhancement, and media generation from Claude Code, Cursor, and other MCP hosts.

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.

MCP server for Audionaut, a free, open-source multitrack audio editor for macOS, Windows and Linux. Agents can split and move clips, set gain, fades and crossfades, time-stretch, work with regions, run audio analysis and Auto Edit, separate stems and export. When the project is open in the app, each edit lands there as one undo step and the project file is never overwritten. Setup: npx -y audionau

Analyze an hour-long YouTube video sentence by sentence in three minutes, and extract the information you need from the screen. Open-source local MCP server for AI clients.

Connects MuseScore Studio 4 to LLM agents so they can read and edit the open score, including notes, rests, tuplets, lyrics, chord symbols, voices, measures, tempo, and mixer settings, through natural language.

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 open, read, edit, verify, and save Aegisub/ASS subtitle documents, covering event lines, styles, timing and QC, karaoke, override tags, vector drawings, clipping, and font metrics. Includes a libass-backed verification layer and byte-faithful round-trips, served over stdio or streamable HTTP.

Exposes a shared video-editing timeline as MCP tools, letting Claude Code, Codex or any MCP client cut, trim, layer, caption, mix and generate motion graphics on the same versioned project the browser editor has open. Every edit an agent makes shows up live, is labelled with its author, and can be undone.

Enables AI agents to drive a full photo-editing engine through validated, non-destructive operations — exposure and colour grading, effects, geometry, text/watermarks, style matching from a reference image, natural-language looks, and batch processing over folders. Originals stay untouched, edits live in an open JSON project format, and everything runs locally without network access unless opted in.