Scrollsnacks

com.scrollsnacksPublished by scrollsnacks.comOfficial publisherv1.0.0Updated Nov 5, 2026

Curated real launch videos split into timed sections (hook, problem, feature, proof, CTA).

VerifiedStreamable HTTPWeb executableProductivity & Workflow Knowledge & Memory Media & Design

Server details

Identifier: com.scrollsnacks/scrollsnacks
Transport: Streamable HTTP
Runtime: Web executable
Trust: Verified
Published: Nov 5, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified that this server's namespace belongs to scrollsnacks.com, which also runs its endpoint. That identifies the publisher; it does not make the server's tools safe.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/com.scrollsnacks%2Fscrollsnacks.svg)](https://sourceweft.com/mcp/com.scrollsnacks%2Fscrollsnacks?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

Hosted library of real launch videos split into timed sections, letting an assistant search references, compare benchmarks and build launch-video scripts and…

What you can do: Search and read launch videos and their timed sections, including motion strips, transcripts and on-screen text
Find opening hooks by formula and get category benchmarks such as duration, hook length and CTA position
List the filter vocabulary of section types, effect labels and style tags
Create, read, update, list and delete stitches of ordered beats with build notes, plus shot lists or build prompts
Add, edit or delete comments pinned to beats or moments in a stitch
When to use it: Use it when planning or scripting a product launch video and you want to study real examples, compare pacing and structure against category norms, or assemble a storyboard from proven sections. It is a planning and scripting aid, not a video generator.
Requirements: Remote streamable HTTP endpoint at scrollsnacks.com/mcp. OAuth 2.1 with dynamic client registration and scope library:read; you sign in with a Scrollsnacks account on first connect. Some tools and fields are limited to the Pro plan.

Before you install

Signing in links your Scrollsnacks account, and stitches and comments you create are stored on the service. Stitch deletion is permanent. Some tools and fields require a paid Pro plan. Library videos belong to their brands and studios.

Installation

In SourceWeft

Open Scrollsnacks in the dashboard and add it to a workspace.
Connect the required credentials. They are stored privately and never shown on public pages.
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.scrollsnacks%2Fscrollsnacks/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": {
    "scrollsnacks": {
      "type": "http",
      "url": "https://scrollsnacks.com/mcp"
    }
  }
}

README

[Scrollsnacks]

Scrollsnacks MCP server and agent skills

Scrollsnacks is a curated library of real launch videos from products and studios. Each video is split into timed sections (hook, problem, feature, proof, CTA), so you can study and reuse what works when you plan your own launch video.

This repo is the public home of the hosted Scrollsnacks MCP server. It holds docs, the registry server.json and a few agent skills. There is no server code here; the server runs at:

Streamable HTTP, OAuth 2.1 with dynamic client registration, scope library:read. You sign in with your Scrollsnacks account the first time your client connects.

Scrollsnacks helps you plan and script. It does not make, generate or render video. Every video in the library belongs to its brand (and studio, where we can confirm it).

Install

Claude (web and desktop): Settings > Connectors > Add custom connector, paste https://scrollsnacks.com/mcp, then sign in.

Claude Code:

Or install this repo as a Claude Code plugin to get the server and the skills together (see .claude-plugin/plugin.json and .mcp.json).

Cursor: add to ~/.cursor/mcp.json (or .cursor/mcp.json in a project):

VS Code (Copilot agent mode): add to .vscode/mcp.json:

ChatGPT: custom remote MCP connectors work through developer mode (Settings > Apps & Connectors > Advanced settings > Developer mode), where available on your plan. Create a connector with https://scrollsnacks.com/mcp and OAuth.

Tools

Some tools and fields are only available on the Pro plan; the tool descriptions say which.

Tool	What it does
`search_videos`	Find launch videos by text, category, style tag, brand or studio. Start here to pick a reference.
`get_video`	One video by id: metadata and timed sections. `view: 'blueprint'` gives beats with durations, words per second and category norms.
`search_sections`	Find sections across videos (CTAs, proof, feature demos) by type, effect, technique, text, category, brand or duration.
`get_section_media`	One section in detail: motion strip image, transcript, on-screen text, optional short MP4.
`search_hooks`	Opening hooks grouped by formula, with category medians for hook length and pace.
`get_benchmarks`	Planning norms for a category: median duration, hook length, when the product is named, CTA position, section shares.
`list_section_types`	The filter vocabulary: section types, effect labels and style tags.
`create_stitch`	Make a stitch: your ordered list of beats from real sections plus your own shots, with a build note per beat.
`get_stitch`	Read a stitch, or get it as a production shot list or build prompt.
`update_stitch`	Change your stitch: title, aspect, visibility or beats.
`add_comment`	Add, edit or delete a note pinned to a beat, a moment or a spot in your stitch.
`list_stitches`	Your stitches, newest first.
`delete_stitch`	Permanently delete one of your stitches.

The server also offers the prompts remake_video, find_examples and audit_script.

Example prompts

"Show me 5 strong hooks from developer tool launch videos."
"Break down how a fintech launch video handles its proof section."
"Find launch videos whose CTA comes in the last 5 seconds."
"Write a 45 second script for my habit tracker, based on 3 similar launches."

Skills

The skills/ folder has Agent Skills (SKILL.md with YAML frontmatter) that use the tools above. Copy a folder into your client's skills directory (for example ~/.claude/skills/ or .cursor/skills/), or install the repo as a Claude Code plugin.

Skill	Use it to
launch-video-script	Write a timed script and shot list from 3 to 5 matching launches.
launch-video-teardown	Break down one launch section by section.
hook-finder	Find strong hooks for a category and draft yours.
storyboard-from-formats	Turn a chosen format into a storyboard with a stitch.
cta-check	Check that your script ends with one clear ask.

Privacy, terms and support

Privacy: https://scrollsnacks.com/privacy
Terms: https://scrollsnacks.com/terms
Support: [email protected]

Skills and docs in this repo are MIT licensed. Launch videos belong to their brands and studios.

Source: README.md at commit 0190b30

Tools

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

v1.0.0LatestNov 5, 2026

Score

75% 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
Declare a license in the repository or the registry entry.