Reeltopus

com.reeltopusPublished by reeltopus.comOfficial publisherv1.2.1Updated Nov 5, 2026

Turn long videos into captioned vertical clips, export them and post them.

VerifiedStreamable HTTPWeb executableCommunication & CollaborationMedia & Design

Overview

AI-generated overview

Remote MCP server that turns long videos into captioned vertical clips, lets an assistant edit and export them, and post or schedule them.

What you can do
  • Upload or find videos and check remaining hours
  • Read ranked clips with transcripts and pick the best ones
  • Edit captions, trims, B-roll and looks
  • Export MP4s, caption files and editor timelines
  • Post or schedule clips to connected YouTube and LinkedIn accounts
  • Run built-in prompts such as clip_and_schedule, best_clips, clip_new_video and post_as_series
When to use it
Useful when you want an assistant to take a long recording and produce short vertical clips end to end: finding or uploading the source, choosing the strongest clip, packaging it and scheduling the post after you confirm.
Requirements
A remote Streamable HTTP endpoint at reeltopus.com/api/mcp; no local package. Sign-in is by OAuth or an API key. A Reeltopus account with remaining hours, and connected YouTube or LinkedIn accounts for posting.
Before you install
It can post and schedule content to connected YouTube and LinkedIn accounts and overwrite existing edits; the README says agents ask before posting or overwriting. Uploaded videos and account data go to the Reeltopus service. Usage is metered in hours, and other platforms require downloading the MP4 yourself.

Installation

In SourceWeft

  1. Open Reeltopus in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.reeltopus%2Fmcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "reeltopus": {
      "type": "http",
      "url": "https://reeltopus.com/api/mcp"
    }
  }
}

README

Reeltopus for AI agents

[mcptry]

Reeltopus turns long videos into captioned vertical clips, exports them and posts them. It works with Claude, ChatGPT, Cursor and any MCP client. This repo holds the install files for agent tools; the server itself is remote: https://reeltopus.com/api/mcp (Streamable HTTP, OAuth sign-in or an API key).

Docs: https://reeltopus.com/docs/api/mcp · Support: [email protected] · Privacy: https://reeltopus.com/privacy

Install

[Add to Cursor] [Install in VS Code]

  • Claude Code (plugin: the server plus two workflow skills): 
    /plugin marketplace add reeltopus/agents/plugin install reeltopus@reeltopus
    Then run /mcp, pick reeltopus and sign in. Or add only the server: claude mcp add --transport http reeltopus https://reeltopus.com/api/mcp
  • Claude (claude.ai, Desktop, mobile): Customize → Connectors → Add → Add custom connector → https://reeltopus.com/api/mcp
  • ChatGPT: chatgpt.com/plugins → + → Add custom MCP server → Public endpoint, the same URL, OAuth.
  • Cursor: the button above, or ~/.cursor/mcp.json: { "mcpServers": { "reeltopus": { "url": "https://reeltopus.com/api/mcp" } } }
  • Gemini CLI: gemini extensions install https://github.com/reeltopus/agents
  • VS Code CLI: code --add-mcp '{"name":"reeltopus","type":"http","url":"https://reeltopus.com/api/mcp"}'
  • Anything else: see llms-install.md.

One line in Claude Code

/reeltopus:clip-and-schedule

or just say "clip my latest video and schedule the best one". Claude finds your newest video (or uploads a file you name), waits for the clips, picks the best one with the packaging that wins on your account, exports it and schedules it after you confirm. Arguments are optional: /reeltopus:clip-and-schedule ~/Movies/ep12.mp4 youtube tomorrow 9am.

The server also offers these as MCP prompts in any client: clip_and_schedule, best_clips, clip_new_video and post_as_series (in Claude Code: /mcp__reeltopus__clip_and_schedule).

What it can do

Check hours, upload or find videos, read ranked clips with transcripts, edit captions, trims, B-roll and looks, export MP4s, caption files and editor timelines, and post or schedule to connected YouTube and LinkedIn accounts (for other platforms, download the MP4). Agents ask before anything that posts or overwrites.

Source: README.md at commit 8fb0fac

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

2
  1. v1.2.1LatestNov 5, 2026
  2. v1.2.0Nov 3, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts