Video MCP servers
MCP servers let Claude, Codex or Cursor drive video tools directly: generation (Higgsfield, Kling), voice (ElevenLabs), or a whole editor. Hosted ones spend credits, so set budgets.
Lab posts (43)
- OpenMotion goes open source: recreate a reference video with your own brand, plus MOTION.md guides
The OpenDesign team officially open-sourced OpenMotion today under Apache-2.0. You hand your coding agent a reference video or a social link, it rebuilds the shots as editable HTML with your brand kit, and you fine-tune the cut in a Studio timeline before rendering an MP4. It ships with 300+ MOTION.md guides and works with 22 local agents.
- Two open TTS models worth knowing for voiceovers (ZONOS3-Mini and Phonon), plus Comfy's official skills plugin for coding agents
A curator list of open repos for a research-to-video-to-voice pipeline flagged two TTS models we hadn't listed. ZONOS3-Mini is Zyphra's Apache-2.0 multilingual voice-cloning model that runs on a GPU, a Mac or in the browser. Phonon is Gradium's tiny on-device model. Separately, Comfy's official skills repo turns Comfy Cloud into slash commands for Claude Code.
- HeyGen Avatar 6 lands at #1 on Avatar Arena and in ComfyUI the same day, plus HyperFrames 0.9.64 and a Miracle update
HeyGen shipped Avatar 6, its new talking-avatar model, on Tuesday morning. Within two hours an independent blind-vote arena had it at #1, and by lunch it was available as a ComfyUI Partner Node. HeyGen's open-source HyperFrames also put out v0.9.64, and Higgsfield posted an update on its Miracle layer editor.
- ffmpeg-skill hits GitHub Trending again: what changed in the 3.x line of the local video editor for coding agents
The free, MIT-licensed skill gives Claude Code, Codex and Cursor 42 FFmpeg tools with typed arguments plus an MCP server, all running on your own machine. It's back on GitHub Trending at about 475 stars a day and passed 6,600 stars. The 3.x line it shipped since our October write-up is worth a look if you tried it before.
- brief2mp4 checks its MP4 against your brief, plus three open-source agent video editors worth knowing: OpenChatCut, Pireel and FireRed-OpenStoryline
A new MIT skill turns a written video brief into a checked MP4 and a report that backs each line of the brief with evidence. Today's agent-editing lists also surfaced three established open-source editors we hadn't listed yet: OpenChatCut, Pireel and FireRed-OpenStoryline.
- MCP for Blender pulls World Labs worlds into Blender 5.3, plus creator-generalist skills and Mirage's Tesseract for agent-built 3D
The most-starred Blender MCP can now generate a whole World Labs Marble world as Gaussian splats inside Blender 5.3, and it ships as a Claude Code plugin. It's on GitHub Trending today. Two newer agent 3D tools landed beside it: codepawl's creator-generalist skill pack and Mirage's Tesseract 0.7.
- Instagram's Edits for Mac has a built-in MCP server, and the community has wired Claude Code into all 274 editor tools
Meta's free Edits editor reached the Mac on Nov 5 with a local MCP automation server, so Claude Code, Codex or Meta's own Muse agent can cut reels inside a real multi-track timeline. A week on, community skills and a bridge plugin are filling the gaps Meta left undocumented.
- Markerboard draws whiteboard explainers to your voiceover, plus a Blender face-capture stack, ComfyUI blockout tips and Kevin Ngo's JavaScript drawing prompt
A brand-new open skill turns a topic into a marker-on-whiteboard explainer timed word by word to the narration. Also today: a Claude-scripted Blender face-capture stack, ComfyUI's advice on how detailed a blockout should be, the prompt behind Kevin Ngo's viral JavaScript drawing, and LTX's write-up of its SDR-to-HDR research.
- Mariko Mori's Claude-coded animation installation, ElevenCreative Dub & Sync, and HyperFrames 0.9.36 to 0.9.39
Three smaller items from overnight. A major artist's retrospective now includes a video piece whose animation Claude wrote as code. ElevenLabs folded dubbing and lip sync into one step in ElevenCreative. HyperFrames shipped four releases covering motion-blur previews, template safety and Studio fixes.
- raea and 67.js: two young render engines built for agents to drive, from React video to path-traced 3D
raea lets an agent write video, motion graphics and 3D as React and TypeScript, then renders it on your own GPU with no browser in the loop. 67.js is an MIT 3D engine an agent edits over MCP, checks with PNG previews, and renders to stills or MP4. Both are weeks old, moving fast and worth a look if Remotion or HyperFrames renders are your bottleneck.
- Taan v1-preview scores music to your cuts, Riverside's Tonality edits a single spoken word, and HyperFrames 0.9.40
Two audio launches aimed at the part of the edit people redo most. Taan, a YC startup, says its music model reads your video's cuts and follows timing instructions like 'drums at 10 seconds', with stems and MCP access. Riverside's Tonality changes one word in an existing recording and keeps the voice and room. HyperFrames 0.9.40 stops long 4K exports from filling your disk.
- Three open-source video tools picking up steam: Mago Studio, Rigby2D and a MiniMax H3 'short-drama workbench' for ComfyUI
None of these is a launch-day headline, but all three are open source, being actively updated and doing real production jobs: a local-first AI video editor that renders through ComfyUI, a free 2D rigging and animation tool with audio lip-sync and an MCP server, and a ComfyUI pack for long, segmented MiniMax H3 videos.
- Adobe MAX 2026 for agent-minded editors: a Creative Cloud MCP preview, SKILL.md skills in Premiere, and Generative Remove for video
At Adobe MAX on Nov 10, Adobe previewed local MCP integrations that let your own agent (Claude, ChatGPT, Gemini and others) work inside native Premiere, After Effects, Photoshop and Illustrator projects. That part is a private beta in early 2027. What you can use today: Premiere's AI Assistant (beta) now runs reusable SKILL.md skills by slash command, plus Generative Remove (beta) for video and a Generative Media Tool in the timeline.
- Claude Fable 5.2 is out: what it means for code-made video, motion graphics and Blender work
Anthropic released Claude Fable 5.2 on Nov 9 for all paid plans and the API (claude-fable-5-2). Within hours, the people who make video with code were posting motion graphics, HyperFrames edits and Blender scenes made with it, and Higgsfield put it behind a 3-day free trial of its MCP. Here is what changed and what it costs.
- Higgsfield Miracle: vectorize a finished clip into editable layers for pixel-level post
On Nov 6, Higgsfield introduced Miracle: proprietary post-production that, per their post, vectorizes any video into layers so you can do localized, pixel-level edits in real time with world knowledge baked in. Private beta for select testers now; they say it is coming to Higgsfield MCP so Claude can call it.
- Viggle Remake: open H3 LoRAs that re-shoot a clip (swap or edit) plus an agent MCP
On Nov 4 Viggle shipped Remake: a video transformation agent with open weights. Per Viggle, two MiniMax-H3 LoRAs (swap and edit) keep the original motion, camera, timing and soundtrack while you recast people, swap objects, or change background, weather, light or style. Hosted app from about $0.96 per 10 s at 720p (their figure); ComfyUI and MCP paths for local/agent runs.
- Scenario's agent skills pack is trending: images, video, audio and 3D from Claude Code, with a price check first
Scenario's MIT-licensed skills repo has been on GitHub's daily Trending list two days running, at #11 overall with about 670 stars today and roughly 2,900 total. It teaches Claude Code, Cursor, Codex and other agents to make images, video, audio and 3D through the Scenario MCP, and it includes the '3D OS' expert teams Scenario announced on Nov 2.
- Runway Dev lands in Claude Code, Codex and Cursor. Here's what the plugin actually does
Runway's Dev plugin is now in Anthropic's official Claude Code marketplace (runway-api@claude-plugins-official), after Cursor and Codex earlier in the week. Some posts describe it as making videos from your terminal. Runway's docs describe something narrower: it helps your agent build Runway's API into your app.
- Kinetograph renders Remotion and HyperFrames projects without a browser
Kinetograph is a beta (v0.3.0) code-to-video engine that runs your TSX in Node and draws each frame with a Rust GPU compositor instead of headless Chrome. Per its creator, existing Remotion projects and HyperFrames HTML pages render as they are.
- Kling 4.0 Flash is open to everyone, including API, MCP and Adobe plugins
Kling announced on Nov 4 that Kling 4.0 Flash, the faster tier of its 4.0 video model, is now available to every user on the Kling website and through the API. It can also be reached through MCP, a CLI and plugins for Photoshop, Premiere Pro and After Effects.
- ComfyUI lands in ChatGPT, and v0.44 adds ProRes saving and MiniMax H3 edit nodes
On Nov 4, Comfy announced that Comfy Cloud is now an official ChatGPT plugin, so you can run ComfyUI image, video, audio and 3D generation from a chat without installing anything or owning a GPU. The v0.44.0 core release that shipped the night before adds ProRes output and a batch of video nodes.
- #OpenSourceHiggsfield final day: six open studios to try
Comfy's open rebuild challenge closes Friday, Oct 30 at 10 AM MDT, and the last 36 hours brought the most complete entries yet. Here are the six worth opening, what each needs to run, and the licences to check.
- kinetograph renders Remotion and HyperFrames projects fast
A new engine renders existing Remotion projects and HyperFrames pages without a browser, using a Rust GPU compositor. Separately, HyperFrames shipped one grade for a whole camera lane, plus a way to bake that grade into a LUT.
- Henge: an open studio for H3 character swap, motion transfer and head swap, plus Higgsfield open-sources its 'Inside AI' short
One day after Comfy's OPENjutsu, LoRA author Alisson Anjos released Henge, an MIT app that drives his own MiniMax H3 LoRAs for swaps, motion transfer and sharpening, with an MCP server for your agent. The same morning, Higgsfield published every prompt and asset behind its new short film.
- EffectCraft: an open-source, After Effects-style compositor in pure Rust that agents can drive over MCP
The ArtCraft team, which also makes FilmCraft and PhotoCraft, has a motion graphics app with compositions, layers, keyframes, 300+ effects, expressions, 3D cameras and lights, Lottie import/export, and a render queue. Every action goes through one command registry, so a CLI, a JSON channel or an MCP server can drive it. It is alpha, Apache-2.0, and passed 7,700 stars in three weeks.
- Concat: an open-source, local-first CapCut replacement that Claude Code can drive through a built-in MCP server
A Rust video editor with local Whisper captions, text-to-speech and voice cloning, background removal, keyframes and 4K export, with no account, watermark or upload. The part we care about: `concat --mcp` lets an agent cut a project with the same commands the window uses.
- Kapwing's MCP lets Claude or Codex caption, translate and voice-clone-dub a video, and the team published three slash-command skills
Add https://www.kapwing.com/mcp as a custom connector in Claude (or a one-liner in Codex), sign in with OAuth, and the agent can upload a clip, burn word-by-word captions, translate them on the original timing, and dub it with each speaker's voice cloned. Kapwing's video ships /captions, /translate and /dubbing skills.
- Local AI transitions between real footage, inside DaVinci Resolve: an honest test of LTX 2.5 and MiniMax H3 Omni vs Seedance 2.5
Kevin Vandermarliere grabs start and end frames from his Resolve timeline, generates car-to-face-to-POV transitions in ComfyUI on a 24 GB RTX 3090, and shows the misses. Then he hides the leftover morphing with speed ramps and Fusion blur.
- BaoCut: an AI video agent where every caption, dub and cut stays editable
Most AI video tools render once and hand you a file. BaoCut makes the timeline the source of truth: transcripts, translations, subtitle layers, voice-overs and code-made motion graphics all live in one editable video that you and your agent edit through the same undo stack.
- Voxtral 3 for video people: cheaper captions that know your product names, and narration with emotion tags
Mistral's Voxtral 3 is pitched at voice agents, but two parts matter for editors: transcription you can bias with product and speaker names, and $13-per-million-character TTS with emotion and pace tags.
- Tandem: an MIT video editor with a CLI and MCP, where agent edits stay purple until you've watched them
Mike Cann had Opus 5.5 build him a native Mac editor overnight to replace Filmora. It's now on GitHub under MIT, with a CLI, an MCP server, a Claude skill, and a review gate that shows exactly what the agent changed.
- VoiceStudio: local voice cloning, dubbing and an MCP server for your video agent
A desktop app (AGPL-3.0) for cloning, voice design, timed video dubbing and transcription in 646 languages. It runs on NVIDIA, Apple Silicon or CPU, and serves an MCP server so Claude Code can voice your renders. Check the model licences first.
- Epic's Unreal Engine plugin for Claude Code is trending. The video angle is Sequencer previs
Hundreds of Unreal Editor tools in 30+ toolsets, including Sequencer, Niagara, materials and Control Rigs, exposed to Claude Code over MCP. It isn't new, but it's #1 on GitHub's Shell trending today, and it opens up agent-built previs and blockouts.
- Four editors your coding agent drives: editonny, BashCut, Yap and free247editor
Agent editing is splitting into styles: a portable skill with 145 motion scenes (editonny), a native Mac timeline with a CLI and MCP (BashCut), a record-and-point toolkit (Yap), and an editor that turns your notes into rules (free247editor).
- Viggle JST-2: 3D characters that need no rig, and motion your agent can ask for
Viggle, the meme-dance app company, launched a world model that builds scenes, characters and motion in 3D instead of pixels. For video makers the useful part is the plain one: a character from one image that is ready to animate, motion from a sentence or a clip, and an MCP server so an agent can fetch both.
- earshot gives coding agents ears: hear the soundtrack, score the sync, forge SFX in code
Agents can now render a whole launch film but can't hear it. earshot is a CPU-only CLI, Python API and MCP server that turns sound into evidence: what a file sounds like, where the hits land against the cuts, and a scorecard with timestamped fixes.
- ComfyArt: a local Lovart-style infinite canvas on your ComfyUI
tldraw + React infinite canvas as a ComfyUI custom node. No account, no credits, no cloud. Optional design agent over MCP. Image plus short video via bundled MiniMax H3 workflows.
- #OpenSourceHiggsfield: Comfy's $25K challenge and the first open rebuilds
Comfy put up $25K for open-source rebuilds of Higgsfield-style apps. Within a day: a camera-move studio, open-weights VFX presets, a script-to-Resolve film studio, and an MCP-only video editor.
- Kling 4.0 is out for everyone, and your agent can drive it through MCP or a CLI
General availability landed on Oct 15 with a new web interface plus MCP and CLI access. For anyone building agent pipelines, the CLI matters more than the model bump.
- Higgsfield inside Claude: MCP, Soul ID and Katana
One connector URL turns Claude into a front end for Higgsfield's models, characters and audio. Katana adds reference-driven edits.
- A two-layer launch video: code motion over a Seedance plate
Recreate a reference launch video's style for your own product, then layer that motion over cinematic footage built in a strict four-step order.
- Ten GitHub repos from one creator's roundup, checked where we could
An open-source 'Adobe suite', a second Photoshop rebuild, an agent browser, a component MCP and more. We've linked only what we could confirm.
- Six motion styles clients pay for, according to Higgsfield
A vendor's map of sellable formats, with the workflow tips worth keeping: storyboard first, HTML design sheets, and a credit tally that includes failed takes.
Skills, repos & workflows in the directory (47)
- OpenMotion Repo
OpenDesign (nexu-io) Apache-2.0 agentic video studio, open-sourced Nov 17 2026 (v0.1.0): give your agent a reference video or social link and it rebuilds the shots as editable HTML with your Brand Kit, then refine in a Studio timeline and render MP4; 300+ MOTION.md shot/timing/transition guides, 150+ brand kits, 22 local agents (Claude Code, Codex, OpenCode, Hermes, Gemini CLI and more), MCP server, ChatGPT plugin, BYOK image/video/music/voice providers; imports HyperFrames projects. Install only from the official repo.
- Comfy Skills Skill
Comfy-Org's official MIT plugins for coding agents: comfy-cloud bundles the hosted Comfy Cloud MCP server plus skills for image, video, audio and 3D generation, voice cloning, background removal, upscaling, consistent characters and searching models, nodes and templates (Claude Code: /plugin marketplace add Comfy-Org/comfy-skills, install comfy-cloud, sign in via /mcp); comfy-sdk is guidance for apps on the Comfy SDK and Router. Runs on your Comfy Cloud plan.
- OpenChatCut Repo
0xsline's AGPL-3.0 local-first desktop video editor (independent open-source ChatCut alternative): built-in agent plus Codex/Claude Code over MCP share the same editing tools on a real multitrack timeline; word-level transcript cuts, linked captions, LUTs, keyframes, WebGL motion templates, person segmentation so captions/overlays avoid the speaker; exports MP4, captions, FCPXML.
- Pireel Repo
AGPL-3.0 open-source AI video editor workbench (canvas, timeline, transcript, captions, assets, AI chat) you run locally or embed in your app as a React component; exports MP4 or a Premiere Pro / DaVinci Resolve timeline. Host supplies model/transcription services; separate Apache-2.0 pireel-agent MCP connector lets Codex or Claude Code drive hosted Pireel Studio.
- FireRed-OpenStoryline Repo
FireRedTeam's Apache-2.0 conversational editing agent: finds and segments footage, drafts storyline and narration, recommends music with beat sync, voiceover and fonts, refines by natural-language edits; save a workflow as a reusable skill for batch edits; ASR rough-cut skill for speech videos; MCP and OpenClaw skills; Hugging Face demo. AI transitions call paid third-party generators.
- SupoClip Repo
FujiwaraChoki's AGPL-3.0 open-source OpusClip alternative: long video (upload, YouTube, Twitch/Kick VOD) → LLM picks 3–7 moments with hook/engagement scores → 9:16 clips with face-centred crop, word-synced captions, hook titles, optional B-roll; editor, MCP server, REST API; Docker self-host (AssemblyAI + LLM key, or local Whisper + Ollama) or hosted.
- Pixelbolt Skill
skulitom's MIT agent-first pixel art and sprite animation toolkit: editable JSON recipes render deterministically to PNG sheets, atlases, APNG, GIF and numbered frames for video editors; CLI, local MCP server, browser studio and a Claude Code skill (npx -y pixelbolt@latest skill install); Node 20+, no API key or image model.
- Markerboard Skill
arifbuildsai's MIT agent skill (Claude Code or any command-running agent) for dry-erase whiteboard explainers: asks whether you supply voiceover/timings, writes a beat-numbered script and waits for approval, makes VO (ElevenLabs, MCP voice tool or local) + word timestamps, then renders one continuous board where a marker draws each mark on its spoken word as the camera follows; eight automated checks; Node + Chromium + ffmpeg on macOS/Windows/Linux.
- insta-edits-for-claude MCP
faisalkhanzemi's MIT Claude Code plugin / stdio MCP bridge for Instagram Edits for Mac's local automation server: refreshes the tool list as Edits switches from 32 home tools to 274 editor tools, keeps the access token in the macOS keychain, readable errors and a doctor command; bundles an edits skill. Unofficial; can't post.
- claude-edits-skill Skill
iamjeeth's MIT Claude Code skill and field manual for the Instagram Edits Mac MCP server (274 tools): timed overlays/cards, beat-placed SFX, styled titles, auto captions, word-level transcripts and jump cuts, preview frames for self-review, working export settings, tracked blur to hide keys in screen recordings. Unofficial.
- MCP for Blender MCP
Siddharth Ahuja's MIT community MCP server + Blender addon (formerly blender-mcp): agents read the scene, run Blender Python, pull Poly Haven/Sketchfab/Poly Pizza assets, generate meshes via Meshy, Tripo, Rodin or Hunyuan3D, and (2.2.8+) generate World Labs Marble worlds as Gaussian splats in Blender 5.3+. Claude Code and Codex plugins; optional paid Premium. Socket has no auth: keep it on localhost.
- 67.js MCP
codepawl's MIT 3D engine for agents: scenes are plain data an agent edits through an MCP server (about two dozen tools, checkpoints, PNG previews) and renders to stills or MP4; Glaze WebGL2 rasterizer for real time, Cook path tracer on CPU/WebGL2/Vulkan for finals; addons for terrain, vegetation, characters, liquid, vehicles. npx 67js-mcp.
- Taan MCP MCP
Taan (YC) v1-preview video-scoring music model via MCP/API: give it a video, script, reference audio, hum or MIDI and it writes an original score timed to your cuts, then edits single instruments or sections; stems + commercial rights, trained on licensed music per the company. Orchestral/cinematic only for now; paid plans from $15/mo.
- Rigby2D Repo
Apache-2.0 2D skeletal animation editor (browser or desktop): AutoRig layered PSD/SVG into bones, meshes and IK; Film workspace with camera, audio tracks, viseme lip-sync via on-device Whisper, renders to PNG/WebM-alpha/MP4; built-in MCP server so Claude can rig and animate; runtimes for Godot, Unity, Phaser, PixiJS and more.
- Viggle Remake Repo
Open MiniMax-H3 LoRAs (swap + edit) from Viggle that re-shoot a clip while keeping motion, camera, timing and soundtrack; hosted app, ComfyUI nodes/int8/GGUF, and an MCP so agents can remake multi-shot films. MiniMax H3 community licence on weights; consent-only use.
- Scenario Agent Skills Skill
MIT skills pack by Scenario for Claude Code, Cursor, Codex and 70+ agents: images, video (Seedance storyboards, music videos, ads, color grade), audio and 3D through the Scenario MCP, with per-job model choice, a cost quote first and an identity library for consistent characters. Includes '3D OS' expert teams that drive Blender, Maya, ZBrush, Unreal and Unity. Generations use Scenario credits.
- Runway Dev plugin MCP
Runway's official plugin for Claude Code, Codex and Cursor: the Runway Dev MCP (OAuth; models, prices, limits, credits, task errors, Model Routers) plus seven skills for building Runway's API into your app. It doesn't generate media itself; your app makes the API calls with your own key.
- Kinetograph Repo
Beta TSX/HTML video engine by 0xS4N4TG: Node runs Remotion-style or HyperFrames code and a Rust GPU compositor draws frames (no Chrome); CLI, MCP server and local editor with agent edits. PolyForm Small Business licence (larger companies need a commercial licence).
- Screenplay (agent-screenplay) MCP
MIT MCP server + CLI by gmpetrov: your agent explores a site or desktop app, writes a scenario, and Screenplay films it Screen Studio-style (smooth cursor, auto zooms, callouts, captions, optional voice-over) to MP4. No model key needed.
- Comfy Previs Repo
MIT browser previs tool by sbobyn (#OpenSourceHiggsfield entry): three.js 3D blockouts, cast reference cards, gamepad/iPhone camera, then storyboard stills and AI video (LTX 2.5, Seedance 2.5, Kling O1, Wan VACE) via Comfy Cloud or local ComfyUI, with per-take cost estimates and a Claude MCP connector.
- Seam ComfyUI
MIT transition studio by @jdnichollsc: two shots (images, clips or a .glb) in, an LTX-2.5 in-between out via ComfyUI; sequences, CLI and a Claude Code plugin (skill + MCP).
- OpenField Repo
wexloops' MIT local Higgsfield-style studio on ComfyUI and open weights: Director shot controls, Scene (local LLM plans and cuts 2-6 shots), Stage (greybox and .glb blocking rendered via the LTX-2.5 layout IC-LoRA), Mirror phone-motion transfer, Reshoot, seam-scored loops, HDR/EXR finishing, 31 MCP tools. NVIDIA 24 GB for video.
- Kitty Open Studio MCP
MIT self-hosted AI video studio on your own ComfyUI: 33 curated open-weights workflows as cards, a timeline editor, and MCP so Claude or ChatGPT can direct a music video. Runs on Runpod (pod or pay-per-second serverless) or your own GPU.
- OpenKatana ComfyUI
Apache-2.0 agent-driven editing engine (Studio, ComfyUI apps, CLI and MCP): photos, footage and music in, a finished edit with cuts, transitions, motion type and music out. On the Comfy Registry; standard editing needs no dedicated GPU, per the FAQ.
- kinetograph Repo
Programmatic video engine for agents: Rust GPU compositor driven from Node renders existing Remotion projects and HyperFrames/HTML pages unchanged, with studio, MCP and still/strip previews. Author's benchmark: 1,184 frames of 1080p in 26 s on a laptop. PolyForm Small Business licence.
- Henge ComfyUI
Alisson Anjos's MIT studio on ComfyUI + MiniMax H3 with trained per-mode LoRAs: character swap, motion transfer (guide latents or TARA), head swap and Sharpness (to 2K/4K). SAM 3.1 multi-character tracking, shot-by-shot long clips, a built-in assistant and an MCP server. Local needs 32 GB VRAM / 64 GB RAM and ~125 GB of models; or RunPod pod/Serverless. Weight and LoRA licenses apply; consent required for real people.
- Scenario for Blender Repo
Experimental GPL-3.0 Blender 5.0+ extension: Scenario image, video (e.g. Seedance 2.5 from your camera move), 3D, PBR, audio and 360 generation from the sidebar, a Blockout text-to-greybox tool and a local MCP server. Needs a Scenario API key; generations cost credits.
- broll-mcp MCP
MCP server for public-domain b-roll from the Internet Archive: brief-driven search with license and trust tier, scene keyframes so a vision model picks the shot, frame-accurate 1–60 s H.264 cuts, and a provenance JSON per clip (source MD5, verbatim license, commercial-use flag, attribution text; unknown licences are marked 'unknown'). No API key; Python 3.12+, uv, ffmpeg. MIT.
- EffectCraft Repo
ArtCraft's open-source After Effects-style compositor in pure Rust: compositions, layers, keyframes, 300+ effects, expressions, 3D cameras/lights, Lottie import/export, render queue. Versioned JSON projects (.ecproj); every action reachable from a CLI, JSON control channel or MCP server. No FFmpeg. Alpha (team says not for client work yet). Apache-2.0.
- ffmpeg-skill Skill
Local video editor for coding agents: 42 FFmpeg/ffprobe tools (cut, join, silence and filler removal, captions/karaoke, reframe, loudness, multicam sync, HDR→SDR, platform exports) with a probe → edit → verify workflow and an MCP server (12 core tools listed by default). `npx ffmpeg-skill` for Claude Code, --cursor / --codex. No cloud or API keys. MIT.
- Kapwing MCP MCP
Official remote MCP (OAuth, any Kapwing plan incl. free, runs on workspace credits) for Claude, Claude Code, Codex and ChatGPT: upload media, grab latest export, burn subtitles, translate subtitles, and AI-dub with per-speaker voice cloning. Kapwing's YouTube walkthrough ships free /captions, /translate and /dubbing skills.
- Concat MCP
Local-first Rust CapCut replacement (macOS/Windows/Linux/Android): local Whisper captions, TTS + voice cloning, background removal, keyframes, 4K60 export, no account or watermark. Built-in MCP server (concat --mcp, window or headless mode) and JSON-RPC API so agents can cut, caption, keyframe and export. Beta; AGPL-3.0.
- BaoCut MCP
Desktop AI video agent (macOS Apple Silicon, Windows) with an editable timeline: local transcription, subtitles, translation, dubbing with vocal separation, filler/retake cuts, HTML motion graphics (baocut/1 and hyperframes/1). Drive it from Claude Code/Codex via skill, MCP or CLI. Source-available Community License (content use free; commercializing the software needs a licence).
- DaVinci Resolve MCP (built-in) MCP
Blackmagic's own MCP server in Resolve Studio 21.1 (File → Setup AI Assistants) for Claude Code, Codex and Claude Desktop. Studio-only, not in the free edition.
- Tandem MCP
Mike Cann's native macOS editor built with Opus 5.5: .tandem JSON projects that you and your agent edit together via CLI, MCP and a Claude/Codex skill. Agent changes stay highlighted until reviewed; imports Filmora projects and agent EDLs. Personal tool, fork it. MIT.
- earshot MCP
Ears for coding agents (CPU-only CLI, Python API, MCP): describe/match/find sounds, a listening timeline with beat grid and sound-to-cut sync, an annotated sheet PNG, a launch-film critique with timestamped fixes, and forge/sfx/kit for code-made SFX (201-sound bank). MIT.
- PINOC MCP (Viggle JST-2) MCP
Remote MCP (Google sign-in) for Viggle's JST-2 3D characters and motion: motion library, text/video-to-motion (1 credit/s, 4 samples), image-to-character with no rigging step. PINOC exports FBX/GLB for Blender, Unity, Unreal, Maya. Paid credits; vendor tool.
- VoiceStudio MCP
Local ElevenLabs-style desktop app: voice cloning, voice design, timed video dubbing, transcription (646 languages) on NVIDIA, Apple Silicon or CPU, with an MCP server at /mcp. App AGPL-3.0; default OmniVoice weights are CC-BY-NC.
- Unreal Engine skills for Claude Code MCP
Epic's official plugin: Claude Code drives the Unreal Editor over Unreal's MCP server (actors, materials, Niagara, Control Rigs, Sequencer and more). Needs ModelContextProtocol + AllToolsets plugins. Useful for agent-built previs/blockouts. MIT.
- BashCut MCP
Native macOS (AVFoundation) video editor with a docked Claude Code/Codex terminal; everything the UI does is available through the bashcut CLI or MCP as undoable operations. Plugins for Whisper captions and silence markers. MIT.
- Yap MCP
macOS record-and-point toolkit: hotkey screen recording with drawn marks and pins, then your agent gets the transcript, frames and audio measurements via CLI/MCP and cuts a captioned demo. No timeline by design. No licence file detected.
- REH (Reverse Engineer Higgsfield) MCP
Rust CLI + local web app + MCP: analyze an AI video (measured shots, cuts, keyframes; model-read prompts labelled as inferred) and write it as a runnable fal.ai flow you can rebuild, verify and batch with your own subjects. MIT.
- YuE2 Studio MCP
Local song generator on YuE2 (via yue2.cpp): full songs with vocals plus an editable sheet-music score you can re-render. Windows app (6 GB+ NVIDIA), MCP server at 127.0.0.1:8791/mcp for agents. MIT.
- kimo MCP
GUI-less video editor driven entirely over MCP: 376 tools for cuts, keyframes, grading, tracking, captions, audio and 3D. Rust core, CPU renderer, tuned for a 2 GB box. MIT.
- Higgsfield MCP MCP
All Higgsfield models, Soul characters, audio, upscaling, Kling Motion Control inside Claude. Uses credits.
- Kling MCP + CLI MCP
Official Kling MCP (https://kling.ai/mcp) and `kling` CLI (npm @klingai/cli-global; China-site accounts use @klingai/cli-cn), plus the official Plugin Skill: the kling-ai-plugin Skill and `kling-plugin` CLI (npm @klingai/plugin-global, or @klingai/plugin-cn for China-site accounts; https://kling.ai/mcp/plugin and https://klingai.com/mcp/plugin). Free to install; generation uses credits from your Global or China Kling account. Proprietary (npm license UNLICENSED), not open source. Text/image/omni-ref video, motion control, reusable Elements, JSON output.
- ElevenLabs MCP MCP
Official MCP for TTS, voices and sound effects.
Pipelines (5)
- HyperFrames product launch video from a URL
- Higgsfield MCP + code motion: two-layer cinematic launch · Based on the creator's video
- Higgsfield: consistent fictional spokesperson with lip-sync
- Higgsfield Katana: rebuild a reference edit with your product
- Higgsfield MCP in Claude: launch, hypermotion and explainer formats · Based on the creator's video