What runtime is required?
Node.js 18 or newer.
CutPro MCP Server
@getcutpro
基本信息
关于 CutPro MCP Server
CutPro MCP server — wraps the public v1 API as MCP tools for AI clients (Claude, ChatGPT, Cursor).
CutPro MCP Server 配置
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"cutpro": {
"command": "npx",
"args": [
"-y",
"@cutpro/mcp"
],
"env": {
"CUTPRO_API_KEY": "<YOUR_API_KEY>"
}
}
}
}CutPro MCP Server 工具
23the workspace this key resolved to, with plan and role.
current credit balance.
ledger of credits added and consumed.
your source video library.
get a presigned URL to upload your own file (max 2 GB; .mp4/.mov/.webm/.mkv).
register a finished upload and get its credit cost.
delete a source video and its submissions.
preview metadata and credit cost of a public URL (free).
start AI clipping (charges credits).
clipping jobs for a video.
poll a submission until completed or failed.
delete a submission and its clips.
clips of a completed submission, rating sorted (URLs opt-in).
apply an editing template to clips in bulk.
delete a single clip.
editing templates to apply to clips.
render a clip to a final MP4.
poll a render until completed.
signed download URL of a completed render.
cancel or delete a render.
render quota for the workspace.
publish rendered clips to connected accounts (immediate or scheduled).
trigger publishing now.
概览
What is CutPro MCP?
CutPro MCP is a Model Context Protocol (MCP) server that turns long videos into viral clips with AI. It exposes the full CutPro API (34 v1 endpoints) as tools, enabling an LLM to analyze a video, clip the best moments, render the final MP4, and publish to TikTok, Instagram, and YouTube.
How to use CutPro MCP?
Install via npx -y @cutpro/mcp and set the CUTPRO_API_KEY environment variable (required for stdio mode). Configure the server in any MCP-compatible client (Claude Code, Cursor, VS Code, Windsurf, Cline, Zed, Gemini CLI, Codex). For hosted access, connect to https://mcp.cut.pro and authorize with OAuth.
Key features of CutPro MCP
- End‑to‑end coverage of all 34 CutPro API tools.
- Token‑efficient results (compact, rating‑sorted, capped).
- Runs locally via stdio or hosted via Streamable HTTP + OAuth.
- Supports multi‑workspace keys with
CUTPRO_WORKSPACE_ID. - Scalable self‑hosted mode with Redis-backed OAuth.
Use cases of CutPro MCP
- Automate AI‑driven video clipping and rendering from a long source.
- Schedule and publish clips to multiple social media accounts.
- Batch process and bulk‑download renders for content repurposing.
- Integrate video editing workflows into AI‑powered assistants.
常见问题
Do I need a CutPro API key?
Yes, a Pro plan and an API key from [cut.pro/studio/me/api-keys](https://cut.pro/studio/me/api-keys) are required.
Can I self‑host the remote endpoint?
Yes, set `MCP_TRANSPORT=http`, `PORT`, optional `MCP_OAUTH=1`, and `MCP_REDIS_URL` for persistence and scaling.
Does the server support OAuth?
Yes, the hosted endpoint (`https://mcp.cut.pro`) uses OAuth 2.1 with PKCE for ChatGPT and Claude.ai.
What video formats are supported for upload?
.mp4, .mov, .webm, .mkv with a maximum size of 2 GB.
开发工具 分类下的更多 MCP 服务器
TranscriptFetch MCP Server
TranscriptFetchModel Context Protocol (MCP) server for TranscriptFetch: fetch YouTube transcripts, search, channels, and playlists from any MCP client.
Termany
thinkany-aiAgent-Native Terminal
174
Casefile
azimov777One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.
3
ArtiBot Cloud MCP - Zhijiangyun 智匠云
bofobArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation
1
JiCo for Jira & Confluence – PII-redacting MCP server with Human-in-the-Loop
drkv-comJiCo for Jira & Confluence: local MCP server for Jira Data Center - redacts personal data before the AI model, holds every write for approval
评论