Nextcut

Created By
Nextcut3 months ago
Nextcut MCP server lets AI agents render videos, stitch clips, add captions, generate slideshows, trim footage, extract thumbnails, and manage templates — all via the Model Context Protocol. Connect Claude, Cursor, Windsurf, or any MCP-compatible agent to automate your entire video production pipeline through a single API key.
Overview

Nextcut MCP Server

Nextcut is a programmatic video rendering API. This MCP server lets AI agents create, edit, and manage videos through natural language.

Features

Render videos from JSON scene definitions with text, images, video, shapes, and animations
Template rendering with dynamic field overrides
Video stitching — concatenate multiple clips seamlessly
Smart stitch — auto-detect silence, remove it, and join clips
Video trimming — extract segments by start/end time
Caption generation — auto-transcribe and burn subtitles
Image slideshows — create videos from images with transitions
Thumbnail export — extract single frames as PNG/JPEG
Video probing — get metadata (duration, resolution, codec)
HTML to image — render HTML strings to PNG

Available Tools (15)

ToolDescription
render_videoRender a video from scenes JSON
render_templateRender from a saved template with field overrides
stitch_videosConcatenate multiple video clips
smart_stitchAuto-detect silence, remove it, and stitch clips
trim_videoExtract a segment by start/end time
extract_thumbnailExport a single frame as PNG/JPEG
add_captionsAuto-transcribe and burn captions
create_slideshowCreate video from images with transitions
probe_videoGet video metadata (duration, resolution, codec)
html_to_imageRender HTML strings to PNG images
list_templatesList all available video templates
get_templateGet full template details
get_render_statusCheck render job status by ID
list_rendersList recent render jobs
get_usageGet account usage, plan tier, and limits

Authentication

Pass your API key via the x-api-key header. Get your key from nextcut.lovable.app/dashboard.

Configuration

{
  "mcpServers": {
    "nextcut": {
      "url": "https://api.nextcut.io/mcp-server",
      "headers": {
        "x-api-key": "YOUR_API_KEY"
      }
    }
  }
}

Compatibility

Works with Claude Desktop, Cursor, Windsurf, OpenClaw, and any MCP-compatible client.

Documentation

Full API docs: nextcut.lovable.app/docs

Server Config

{
  "mcpServers": {
    "nextcut": {
      "url": "https://api.nextcut.io/mcp-server",
      "headers": {
        "x-api-key": "YOUR_API_KEY"
      }
    }
  }
}
Project Info
Created At
3 months ago
Updated At
3 months ago
Author Name
Nextcut
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago