Describe it
Tell your agent what the video should feel like, what to stress, which examples you like.
MCP server for video editing
MCP server for video editing: Claude and ChatGPT edit Reels and Shorts
Connect your AI agent to Captions Space. Describe the video you want and share examples you like — the agent directs, our studio transcribes, renders and shows it the result. You watch the edit live in the editor.
- Server URL
- https://api.captions.space/mcp
- Transport
- Streamable HTTP
- Authorization
- OAuth (claude.ai, ChatGPT) or an API key in the Authorization header
- Clients
- Claude, ChatGPT, Claude Code, Cursor, Codex and other MCP clients
- Tools
- 21 tools: speech, scenes, frames, edit, assets, preview, export
What the Captions Space MCP server is
MCP (Model Context Protocol) is the standard way for AI assistants to use outside tools. Our MCP server turns Captions Space into an editing studio for your agent: it gives the model what it cannot do itself — hear the speech, see the frames, know exact timings — and renders whatever the model decides.
The agent stays the director: it plans hooks, accents, emoji, zooms and b-roll from your brief. The studio computes pixels and milliseconds, keeps subtitles off faces and renders the video exactly like the final file.
How AI video editing over MCP works
The agent reads the video
Transcript with word timings, cuts, faces and objects, frame sheets — everything a director needs.
It directs
Style, accents, hooks, emoji, effects, zooms, b-roll, sounds. It brings its own assets and saves the edit.
Checks and iterates
Renders fragments exactly like the final file, looks at them and fixes. You see every change live in the editor.
What your agent can do
Animated subtitles
Pick a template, pace and highlighted words; fix any word of the transcript.
Text, emoji and effects
Hooks and titles, emoji next to the speaker, confetti, fire, transitions on cuts.
Zooms and b-roll
Punch-ins on the strongest word, slow pushes, cutaways from its own clips and images.
Sounds and music
Whooshes and hits from our library, your own music track at the right volume.
Its own assets
Images, GIFs, clips and music the agent found or generated elsewhere go straight into the edit.
Translation
Subtitles in 37 languages with the timing kept.
How to connect the MCP server
https://api.captions.space/mcp
claude.ai and ChatGPT
Add a custom connector with the server URL below and sign in to Captions Space when asked — no key needed.
Claude Code
claude mcp add --transport http captions-space https://api.captions.space/mcp \ --header "Authorization: Bearer cs_live_…"
Cursor and other clients with mcp.json
Use a key from Developers:
{
"mcpServers": {
"captions-space": {
"url": "https://api.captions.space/mcp",
"headers": {
"Authorization": "Bearer cs_live_…"
}
}
}
}Example request to your agent
Edit my video into a 30-second Reel: put the strongest line first, bold yellow subtitles, an emoji on every joke, a punch-in zoom when I say the price, and keep the bottom free for Instagram's UI. Show me frames before exporting.
All MCP server tools
| Tool | What it does |
|---|---|
editing_guide | How to edit: workflow, the edit document, ready recipes |
list_videos / get_video | Projects, status and the editor link |
create_video / start_processing | A new video by link or by file |
wait_for_video | Wait for processing to finish |
get_transcript | Words with ids and timings, phrases |
get_scenes | Cuts, who and what is in frame, emotion |
get_frames | A sheet of source frames — the agent's eyes |
get_edits / save_edits | The whole edit, versioned |
upload_asset_from_url / request_asset_upload | Your b-roll, images, GIFs, music and sounds |
add_emoji | Emoji stickers |
render_preview / wait_for_job | Render a fragment exactly like the file and look at it |
list_styles / get_catalog | Subtitle templates, effects, transitions, sounds |
export_video / list_exports | MP4, MOV, WebM, SRT, VTT, ASS |
account_info | Plan and credits left |
Your editor is the agent's studio
- Open the project in the editor: every save of the agent appears on your screen by itself.
- Edit by hand at the same time — the agent's saves never silently overwrite yours, and yours never overwrite the agent's.
- When the agent is done, the result is a normal project: tweak a word, export any format.
How much it costs
- 1 credit
- one started minute of processed video
- 0 credits
- edits, frame sheets, previews and exports — iterate as much as you need
Try it free: Free gives 6 credits a month, videos up to 6 minutes and MP4 with a watermark. Pro gives 1000 credits per period, videos up to 30 minutes and every format.
See plans →MCP server FAQ
It is a set of tools an AI assistant can call through the Model Context Protocol. Captions Space gives the assistant the transcript, scenes and frames of your video and renders the edit it decides on: subtitles, text, emoji, effects, zooms, b-roll and sounds.
Beautiful captions.
Better videos.
Captions Space generates AI subtitles, styles them with designer presets and exports the finished video.
Create captions →No credit card required
- ✓ Free plan available
- ✓ One-click instant export
- ✓ Built for creators
Runs in the browser — no install, no credit card, and a free plan with 6 minutes of video a month.