Log inSubmit server
CutPro logo

CutPro

Turns video sources into AI-selected clips, rendered MP4s, and published social posts through CutPro.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install CutPro

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "cutpro": {
      "command": "npx",
      "args": [
        "-y",
        "@cutpro/mcp@latest"
      ],
      "env": {
        "CUTPRO_API_KEY": "YOUR_VALUE_HERE",
        "CUTPRO_WORKSPACE_ID": "YOUR_VALUE_HERE",
        "CUTPRO_API_URL": "YOUR_VALUE_HERE",
        "MCP_TRANSPORT": "YOUR_VALUE_HERE",
        "PORT": "YOUR_VALUE_HERE",
        "MCP_OAUTH": "YOUR_VALUE_HERE",
        "MCP_PUBLIC_URL": "YOUR_VALUE_HERE",
        "MCP_REDIS_URL": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

We couldn’t confirm it starts correctly

The install command started, but didn't respond the way we expected when we tried to talk to it.

npx -y @cutpro/mcp@latest

Failed to parse URL from allmcps-placeholder/openapi.json

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 8d ago.

Overview

CutPro MCP server exposes the CutPro API for analyzing videos, creating AI clipping jobs, rendering clips, and publishing posts. It runs locally over stdio with an API key or remotely over Streamable HTTP with OAuth. Use it when an agent needs to move from a long video or public URL to finished, downloadable, or published clips. Processing, rendering, and publishing consume workspace resources or credits where applicable.

Use cases

  • Analyze public videos before spending clipping credits
  • Upload long-form video files for AI clipping
  • Render selected clips as downloadable MP4 files
  • Schedule or publish clips to connected social accounts

Key features

  • AI video clipping workflow
  • Video uploads and public-URL analysis
  • Template application and MP4 rendering
  • Credit and render quota tracking
  • Immediate and scheduled post publishing
  • Local stdio and hosted OAuth modes

Tools80

What CutPro lets your agent do. Expand a tool for its parameters.

Self-reported~750 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

10/10 checks healthy over the last 54d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 12d ago via OSV.dev · @cutpro/mcp@latest (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars2Stargazers on the source repository.
npm downloads1.1kPackage downloads in the last 30 days.
Last commit1d agoMost recent push to the default branch.
Install checkInconclusiveStarted but did not complete the MCP handshake in our test.
Tools exposed80Callable tools this server registers over MCP.

How CutPro works

What the CutPro MCP server does

The CutPro MCP server connects MCP-compatible clients to CutPro’s video processing API. It supports the workflow from source media through publication: inspect a public video URL or upload a local file, start AI clipping, review the resulting clips, apply templates, render final MP4 files, and publish posts to connected accounts.

It also exposes workspace and account operations. Agents can check the resolved workspace, user role, plan, credit balance, and credit ledger; browse source videos, clipping submissions, clips, templates, and render limits; and remove videos, submissions, clips, or renders when needed.

How it works

The local package is installed and launched with npx -y @cutpro/mcp@latest. It communicates with the client over stdio and sends requests to the CutPro API. A typical workflow starts with analyze_video for a public URL or an upload using start_upload and complete_upload. The agent then calls submit_clipping, checks progress with get_submission, lists the completed clips, and optionally applies a template before rendering.

Rendering is asynchronous. render_clip starts the job, get_render checks its status, and get_render_download returns a signed download URL after completion. Publishing uses create_post to prepare an immediate or scheduled post and publish_post to trigger publication. Tools that spend credits, publish content, or modify data should be treated as state-changing operations.

The tool set is generated from CutPro’s OpenAPI specification. This keeps endpoint parameters, descriptions, responses, and operation names aligned with the API. File-upload tools that require bytes from disk are available through the local server rather than chat-based clients.

Setup and configuration

The CutPro MCP server requires Node.js 18 or newer, a CutPro account on the Pro plan, an API key, and an MCP-compatible client for local use. Configure CUTPRO_API_KEY in the client’s MCP server environment. CUTPRO_WORKSPACE_ID can select a workspace when one key has access to multiple workspaces, while CUTPRO_API_URL can replace the default API base URL.

The hosted endpoint is available at https://mcp.cut.pro for ChatGPT and Claude.ai. Hosted users sign in to cut.pro, choose a workspace, and approve the connection instead of configuring a local API key. Any CutPro plan can connect to the hosted service, with jobs using the selected workspace’s credits.

For self-hosting, set MCP_TRANSPORT=http; MCP_OAUTH=1 enables OAuth 2.1 for browser clients. MCP_PUBLIC_URL identifies the public endpoint, and MCP_REDIS_URL stores OAuth state across restarts and instances. Without Redis, state remains in memory and is lost when the process restarts.

Tools and capabilities

  • Inspect workspace identity, role, plan, credit balance, and balance history.
  • List, upload, analyze, and delete source videos.
  • Start, monitor, list, and delete AI clipping submissions.
  • Browse clips, apply editing templates, and remove individual clips.
  • Render clips, monitor render status, download completed files, and cancel renders.
  • Create and publish immediate or scheduled posts to connected accounts.
  • Check workspace render quotas and browse available templates.

Limitations and notes

The local setup requires a Pro plan and API key. Uploaded files must be MP4, MOV, WebM, or MKV and cannot exceed 2 GB. Public-URL analysis is free, while clipping and other operations may consume credits. Hosted OAuth avoids local installation and API-key configuration, but it still uses the selected workspace’s credits. Self-hosted OAuth without Redis is intended for a single instance because authorization state does not survive restarts.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about CutPro

CutPro is an MCP server that connects AI clients to the CutPro API for video analysis, AI clipping, template application, rendering, and publishing. Its tools can inspect workspaces and credits, manage source videos and submissions, retrieve completed clips, generate downloadable MP4s, and create or publish posts to connected accounts.

Install it by configuring your MCP client to run `npx -y @cutpro/mcp@latest` and provide `CUTPRO_API_KEY` in the server environment. Local use requires Node.js 18 or newer, a CutPro Pro account, an API key, and an MCP-compatible client.

Yes, CutPro works with Cursor through its local stdio configuration. Add the server command and `CUTPRO_API_KEY` to Cursor’s MCP settings, using the same configuration pattern as other local clients.

Yes, use the hosted endpoint at `https://mcp.cut.pro` with ChatGPT or Claude.ai. Sign in to cut.pro, select a workspace, and approve the connection; the hosted flow does not require local installation or an API key.

Related MCP servers

All in Multimedia Process All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewCutPro AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/cutpro?style=directory)](https://allmcps.com/mcp/cutpro)
HTML Embed
<a href="https://allmcps.com/mcp/cutpro"><img src="https://allmcps.com/api/badge/cutpro?style=directory" alt="CutPro on AllMCPs" /></a>