Para agentes
Un servidor MCP que edita vídeo. Nada sale sin ti.
Apunta tu agente a vidcut y obtendrá una línea de tiempo real, no un chat. También te obtiene a ti — en el navegador, aprobando antes de que se renderice nada.
Actualizado 2026-09-10
¿Qué es un editor de vídeo MCP?
El Model Context Protocol (MCP) es un estándar abierto para conectar modelos de IA con herramientas externas, usado por Claude Code, Claude Desktop, Cursor y una lista creciente de clientes de agentes. vidcut incluye un servidor MCP: en lugar de un chat pegado a un editor, tu agente llama a 53 herramientas estructuradas directamente sobre una línea de tiempo real y editable — vertical, horizontal, cuadrada o 4:5 — importando material, cortando y reordenando clips, poniendo subtítulos palabra a palabra, añadiendo motion graphics, mezclando audio y renderizando con FFmpeg. Cada herramienta devuelve el estado estructurado del proyecto, así que el agente nunca re-describe el vídeo desde una transcripción. Y cada cambio aparece en una interfaz de navegador con revisión humana: el agente llama a request_review y espera, tú apruebas o devuelves la edición con notas que él lee, y nada se renderiza sin tu visto bueno. La versión autoalojada es gratuita bajo la AGPL; la nube añade renderizado, almacenamiento y más herramientas.
No todos los servidores MCP de vídeo funcionan así.
vidcut es de código abierto bajo la AGPL y se ejecuta en tu propia máquina. Expone una línea de tiempo real y editable — no una cola de renderizado — y tiene una compuerta de revisión: el agente llama a request_review y espera, y tú devuelves el trabajo con notas que él lee. No apruebas un archivo terminado; estás dentro de la edición mientras ocurre.
Cómo conectarlo
Nube
Un comando. Todos los planes de pago incluyen un endpoint MCP remoto.
claude mcp add --transport http vidcut https://your-editor.studio.usevidcut.com/mcpAutoalojado
Ejecuta la versión AGPL en tu propia máquina y apunta tu agente ahí: sin cuenta y sin límites.
Lee el códigoLas 53 herramientas
Cada herramienta devuelve el estado del proyecto de forma estructurada, así tu agente nunca tiene que volver a describirse el vídeo a sí mismo.
| Herramienta | Qué hace |
|---|---|
add_clip | Append already-imported media to the end of the main track (existing clips are untouched — good for adding one file at a time) |
add_mographnube | Add one parameterized motion-graphics overlay (the others are untouched) |
add_overlay | Add a single overlay (the others are untouched) |
add_to_library | Save media into the user's cross-project library for reuse in future projects |
auto_caption | One-shot auto captions: recognize → paginate → write the caption track (a whole-track replace |
export_publish_package | Package the finished render for manual upload: copies the output video plus cover and .srt into output/publish/<stamp>/, writes one text file per platform from the metadata you provide, and records per-platform duration/size warnings in manifest.json |
extract_audio | Extract a clip's audio into a standalone audio item (the clip's own volume goes to zero), so it can be adjusted, faded or deleted on its own |
generate_imagenube | Generate NEW images with AI via fal |
generate_musicnube | Generate a NEW background-music track with AI via fal |
generate_soundnube | Generate a NEW custom sound effect with AI (ElevenLabs SFX v2 via fal) |
get_chatsolo lectura | Read the conversation with the person reviewing your work (both sides, oldest first) |
get_editing_skillsolo lecturanube | Fetch one editing playbook in full (markdown): workflow with tool-call sequences, silent-failure pitfalls, final checklist |
get_editor_contextsolo lectura | The user's current selection in the UI, playhead position, and dragged time range |
get_feedbacksolo lectura | Summary of human changes since the given version — how the AI reads back what the user adjusted |
get_framesolo lectura | Extract the frame at a given time as JPEG — the AI's eyes |
get_generation_statusnube | Check AI generation jobs |
get_historysolo lectura | Recent change log (version/label/source/ts) |
get_mograph_snippetsolo lecturanube | Fetch one library item's full HTML/CSS/GSAP source plus an adaptation checklist for the html mograph template (strip the page scaffold and every <script src>, register the paused window.__timelines["html-mograph"] timeline, re-layout 1920x1080 blocks for the bake canvas, swap webfonts and bundled images) |
get_projectsolo lectura | Trimmed overview of the project (clips/captions/media/version/review) |
import_from_library | Import a library asset into this project: its derivatives are copied in (no re-processing) and the file is referenced in place from the library (content-addressed, so the reference never breaks) |
import_media | Register a media file |
import_stock_medianube | Download one search_stock_media result into the project and register it as media (builds proxy/filmstrip/peaks |
list_editing_skillssolo lecturanube | List the built-in editing playbooks — 8 workflows covering speech editing, transcript-driven assembly, style mimicry from a reference video, beat-synced cutting, music & mixing, long-to-short repurposing, short-form packaging and pre-render checks |
list_librarysolo lectura | Search the user's cross-project asset library (reusable logos, intros, BGM…) |
list_sourcesolo lectura | List importable files in a footage folder (no recursion, hidden files excluded, whitelisted extensions only) |
post_chat | Say something to the person reviewing your work — it shows up in the Chat tab of the editor and they can reply there |
preflight_checksolo lecturanube | Read-only self-check of the current timeline, to run right before render |
redo | Redo the last N undone edits (the inverse of undo) |
remove_audio | Remove one audio item |
remove_clip | Remove one clip (the magnetic main track closes the gap, so every later clip shifts left) |
remove_mographnube | Remove one mograph overlay |
remove_overlay | Remove one overlay |
render | Render the project to a final mp4 (the project canvas, currently 1080×1920, re-encoded) |
reorder_clips | Reorder the main-track clips (order is a permutation of clipIds) |
request_review | Ask the user to review the current timeline in the browser UI |
search_mograph_librarysolo lecturanube | Search the vendored motion-graphics snippet library (373 HTML/CSS/GSAP items from the hyperframes registry), organised into 13 categories (lower-third / text-type / chart-data / map-geo / social-mock / device-ui / transition / vfx-overlay / code-dev / handwriting / logo-brand / background / camera-motion) |
search_stock_mediasolo lecturanube | Search free stock-media platforms (Pexels, Pixabay, Unsplash, Freesound) for B-roll, photos, sound effects and music beds |
set_audio | Set the whole audio track (voiceover/BGM |
set_canvas | Change the canvas size (the frame everything is composed into, and the shape of the exported video) |
set_canvas_fit | What to do when the media does not fill the canvas: contain = black bars, blur = a blurred, scaled-up fill (blur is the better look for landscape footage on a 9:16 canvas) |
set_captions | Replace the whole caption track (every existing caption is replaced |
set_cover | Set the cover image: when a rendered file is still around, the frame at that time is taken from the export (overlays and captions included) |
set_overlays | Replace the whole overlay track (every existing overlay is replaced |
set_timeline | Set the whole video main track (the initial cut) |
timeline_op | Rough-cut at a point on the timeline: split, deleteBefore (drop the picture before that time), deleteAfter (drop what follows), or freeze (insert a freeze-frame) |
transcribe | Run speech recognition (whisper.cpp) over the whole timeline and return per-word timestamps |
undo | Undo the last N edits (cursor-style: call it repeatedly to keep walking back) |
update_audio | Adjust one audio item (volume, fades, timing, ducking) |
update_caption | Change one caption only (text/start/duration/style/tokens/reveal/motion) |
update_clip | Change one clip's in/duration/volume/label/transition (its position in the main track is untouched) |
update_library_asset | Rename or retag a library asset (label/tags are what list_library searches) |
update_mographnube | Change one existing mograph overlay: props (shallow merge — send only the fields you want to change), duration, position, start or anchor |
update_overlay | Change one overlay only (start/anchor/duration/position/text) |
Generada a partir de la superficie de herramientas registrada, así que esta tabla no puede desviarse de lo que el servidor expone realmente. La versión de código abierto que autoalojas incluye 39 de ellas; las marcadas como «nube» requieren un plan de pago.
¿Listo para dirigir?
Devolución íntegra en 7 días, sin encuesta de salida.