--- title: 'How to Automate Video Editing with MCP - OpenClip' description: 'Automate video editing with MCP: connect an assistant to OpenClip, submit videos with submit_video, and render captioned clips with render_clip.' canonical: 'https://openclip.app/guides/automate-video-editing-with-mcp' markdown: 'https://openclip.app/guides/automate-video-editing-with-mcp.md' --- Part of OpenClip's video editing MCP resource hub Explore setup guides, assistant workflows, examples, and prompt templates for controlling OpenClip from MCP-compatible AI assistants. [Open MCP hub](/mcp)MCP Guide # How to Automate Video Editing with MCP This guide builds a real assistant-led clipping pipeline: connect your AI assistant to OpenClip's MCP server, submit a long video, let the platform detect the best moments, and render the ones you approve as captioned vertical clips. Every step uses the actual tool calls, so you can follow along in Claude, ChatGPT, Cursor, or Perplexity. Beginner 20 minutes (plus processing time for your video) Assistant-led video clipping automation ## Prerequisites - An OpenClip account with an active subscription (processing uses credits, counted in minutes) - An MCP-compatible assistant: Claude, ChatGPT (paid plan with Developer mode), Cursor, or Perplexity (Pro and up) - A long-form source video: a public URL from a supported provider or a local file ## Steps 1 ### Connect your assistant to the server Add [https://openclip.app/mcp](/mcp) to your client and sign in with your OpenClip account when the OAuth prompt appears. In Claude that is Settings, Connectors, Add custom connector; in Claude Code run claude mcp add --transport http openclip [https://openclip.app/mcp](/mcp); in Cursor add {"mcpServers": {"openclip": {"url": "[https://openclip.app/mcp](/mcp)"}}} to mcp.json. One URL for everyone, no API key. 2 ### Brief the assistant and submit the video Tell the assistant the source, target platform, audience, and how many clips you want, then let it call submit\_video with the URL (use list\_supported\_providers if you are unsure the source is accepted, or create\_upload plus complete\_upload for a local file). Resubmitting the same URL within 24 hours returns the existing run instead of double-charging credits. 3 ### Poll processing status Processing is asynchronous: OpenClip downloads, transcribes, detects moments, and tracks speakers while the assistant polls get\_video\_status every 10 to 15 seconds. Statuses move through downloading and processing to completed. If a video fails immediately, there is usually no active subscription; pending\_credits means the team is out of processing minutes. 4 ### Review the detected moments When the video completes, have the assistant call list\_clips and present the detected viral moments with their virality scores, titles, and hooks. The titles and quotes come from your video and are marked untrusted content, so the assistant shows them for your judgment rather than acting on them. Pick the moments worth publishing. 5 ### Render the approved clips For each approved moment the assistant calls render\_clip, optionally with a caption preset; have it run list\_caption\_presets once and remember your house style. Rendering is asynchronous too, so it polls get\_render\_status until each clip reports completed, then hands you the clip URLs. 6 ### Make it repeatable Save your preferences as a processing agent with create\_agent (caption preset, composition settings, even a logo watermark), then pass that agent to future submit\_video calls. Track spend with get\_usage; credits are minutes of processing, 150 per month on Starter and 300 on Pro. ## What You'll Achieve A repeatable workflow where your assistant turns any long video into a reviewed batch of captioned, publish-ready clips ## Features ### End-to-end tool chain submit\_video, get\_video\_status, list\_clips, render\_clip, get\_render\_status: five tool calls take a raw URL to reviewed, captioned clips. ### Async by design Video processing takes minutes, not seconds. The polling pattern keeps your assistant responsive and honest about progress instead of pretending edits are instant. ### Moment detection included You do not tell the assistant where to cut. OpenClip scores the moments; the assistant's job is presenting them and rendering the ones you approve. ### Captions as a parameter Caption style is one argument on render\_clip. Pull the valid preset keys from list\_caption\_presets and standardize your look across every clip. ### Presets for repeat shows Processing agents created with create\_agent make episode two identical to episode one: same tracker, same captions, same branding, no re-briefing. ### Predictable cost Credits are minutes of processing, visible any time via get\_usage, and duplicate submissions within 24 hours reuse the existing run instead of burning credits. ## Frequently Asked Questions ### Which assistants can run this workflow? Any MCP client: Claude (web, Desktop, Claude Code), ChatGPT with Developer mode on a paid plan, Cursor, Perplexity Pro and up, and agent frameworks that speak MCP. The tool calls are identical everywhere because the server is the same. ### How long does processing take? It depends on source length. The assistant should poll every 10 to 15 seconds and, if nothing changes after about 15 minutes, stop and suggest retrying later rather than spinning forever. ### Can I automate the review step away? You can render everything list\_clips returns, but we recommend keeping a human approval step. Moment titles and hooks are generated from your video, and brand judgment (what should ship) is exactly the part you do not want to delegate. ### What breaks most often, and what is the fix? Three failures cover almost everything: an instant failed status means no active subscription; pending\_credits means top up your processing minutes; download\_failed means the source URL is not fetchable, so check it against list\_supported\_providers. Our troubleshooting guide covers the rest. ## Automate your first video today Connect OpenClip to your assistant and turn one long video into a week of clips before your next meeting. [Get Started Free](https://openclip.app/register) ## Related Pages ### Glossary [Model Context Protocol for Video Editing](/learn/model-context-protocol-video-editing) [Video Editing MCP Server: What It Is and How to Connect](/learn/video-editing-mcp-server) ### Guides [Claude Video Editing Workflow: A Worked MCP Example](/guides/claude-video-editing-mcp-workflow) [Troubleshoot Video Editing MCP Workflows](/guides/troubleshoot-video-editing-mcp-workflows) ### Templates [MCP Video Clipping Prompt Template (Copy-Paste)](/templates/mcp-video-clipping-prompt-template) ### Examples [Podcast MCP Video Workflow Example](/examples/podcast-mcp-video-workflow-example) [Webinar MCP Clip Workflow Example](/examples/webinar-mcp-clip-workflow-example)