About OpusClip
OpusClip MCP is a hosted MCP server for creators turning long videos into short clips ready for posting. It also handles captions, thumbnails, social copy, and scheduling posts to connected accounts.
Key features
- 01Select clips from a video file or URL
- 02Trim, reframe, and caption clips
- 03Retrieve video transcripts
- 04Generate thumbnails and social copy
- 05Schedule or publish social posts
Use cases
- 01Break long videos into short clips
- 02Caption vertical social videos
- 03Create titles and hashtags for clips
- 04Schedule clips on connected accounts
MCP support
It is a hosted MCP server accessed over Streamable HTTP with OAuth, with launchers that proxy stdio to the hosted endpoint. MCP clients can call its video editing, transcription, copywriting, and publishing tools.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.opus.pro/mcpclaude mcp add --transport http opus-pro-opusclip https://mcp.opus.pro/mcp{"mcpServers":{"opus-pro-opusclip":{"type":"http","url":"https://mcp.opus.pro/mcp"}}}Open in Cursor{"servers":{"opus-pro-opusclip":{"type":"http","url":"https://mcp.opus.pro/mcp"}}}Open in VS Code{"mcpServers":{"opus-pro-opusclip":{"type":"http","url":"https://mcp.opus.pro/mcp"}}}{"mcpServers":{"opus-pro-opusclip":{"serverUrl":"https://mcp.opus.pro/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMEOpusClip MCP
Turn long videos into AI-curated short clips — from your agent. Submit a video file or URL and OpusClip finds the best moments, adds captions, reframes to vertical, and returns ready-to-post clips. It can also generate thumbnails and social copy, pull transcripts, and schedule posts to your connected social accounts.
OpusClip is a hosted (remote) MCP server — nothing to build or run locally. Authentication is OAuth, handled in the browser on first use. No API keys required.
- Endpoint:
https://mcp.opus.pro/mcp(Streamable HTTP + OAuth) - Docs: https://help.opus.pro/api-reference/agent-setup
Quick start
Add OpusClip to your MCP client's config:
{
"mcpServers": {
"opusclip": {
"url": "https://mcp.opus.pro/mcp"
}
}
}
For stdio-only clients, use the npm launcher instead:
{
"mcpServers": {
"opusclip": {
"command": "npx",
"args": ["-y", "@opusclip/mcp"]
}
}
}
Or the PyPI launcher, if you prefer Python tooling (uvx):
{
"mcpServers": {
"opusclip": {
"command": "uvx",
"args": ["opusclip-mcp"]
}
}
}
Both launchers proxy stdio to the hosted endpoint via mcp-remote, so the Python launcher also needs Node.js >= 18 on PATH.
On the first tool call, a browser window opens to sign in to your OpusClip account and approve access.
Per-client setup
| Client | How |
|---|---|
| Claude.ai / Claude Desktop | Settings → Connectors → add a custom connector with the URL above |
| Cursor | Settings → Tools & MCP → New MCP Server, or the one-click Add to Cursor button in our docs |
| Cline | Add the config above to cline_mcp_settings.json (see llms-install.md) |
| Claude Code | claude mcp add --transport http opusclip https://mcp.opus.pro/mcp |
What you can do
- Curate — submit a video (file or URL) and get AI-picked clips scored for virality
- Edit — apply an editing script (trim, reframe, layout, captions) to a clip
- Caption & transcript — pull the transcript, generate styled captions
- Thumbnails — generate thumbnail options for a clip
- Social copy — generate titles, descriptions, and hashtags per platform
- Collections — group clips and export them
- Schedule & publish — post or schedule clips to connected social accounts
- Usage — check your remaining credits and plan
See the full tool reference in the OpusClip API docs.
Registry
This server is listed in the official MCP Registry as io.github.opus-pro/opusclip
(see server.json).
License
MIT © Opusclip Inc.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.