About drop
drop is a remote MCP server for publishing HTML pages from an AI assistant and sharing them by URL. It supports page updates and workspace visibility controls, with a local CLI for uploading files the server cannot access.
Key features
- 01Publish HTML pages with shareable URLs
- 02Update pages without changing their URLs
- 03List, fetch, and delete workspace pages
- 04Set pages to public or workspace-private
- 05Upload local files with drop-upload CLI
Use cases
- 01Share an assistant-generated report or dashboard
- 02Revise a published page while retaining its URL
- 03Embed an uploaded screenshot or PDF in a page
MCP support
The remote MCP server exposes tools to publish, update, list, fetch, and delete pages. The drop-upload CLI provides HTTPS URLs for local files that the remote server cannot read.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://drop.neuronik.io/mcpclaude mcp add --transport http io-neuronik-drop https://drop.neuronik.io/mcp{"mcpServers":{"io-neuronik-drop":{"type":"http","url":"https://drop.neuronik.io/mcp"}}}Open in Cursor{"servers":{"io-neuronik-drop":{"type":"http","url":"https://drop.neuronik.io/mcp"}}}Open in VS Code{"mcpServers":{"io-neuronik-drop":{"type":"http","url":"https://drop.neuronik.io/mcp"}}}{"mcpServers":{"io-neuronik-drop":{"serverUrl":"https://drop.neuronik.io/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 README
drop
Publish web pages straight from your AI assistant — and share them with a link.
drop.neuronik.io · MCP-native · works with Claude, Cursor & any MCP client
Your AI assistant writes great HTML — reports, dashboards, prototypes, docs. drop is a remote MCP server that publishes it as a real, hosted web page the moment you say "drop this". No copy-paste, no hosting setup, no redeploys on edits.
This repo is drop's public home: setup instructions, the drop-upload CLI source, and the issue tracker for feedback and bug reports. (The drop cloud service itself is not open source.)
Quick start
-
Sign in at drop.neuronik.io — Google or email magic link. You get a workspace; teammates on the same email domain share one.
-
Connect your assistant to the MCP server:
https://drop.neuronik.io/mcpClaude Code
claude mcp add --transport http drop https://drop.neuronik.io/mcpThen run
/mcp, select drop, and complete the browser sign-in.Claude Desktop / Claude.ai
Settings → Connectors → Add custom connector → paste the URL → Connect → sign in with Google.
Cursor
Settings → MCP → Add new MCP server, or use:
{ "mcpServers": { "drop": { "command": "npx", "args": ["mcp-remote", "https://drop.neuronik.io/mcp"] } } }Any other MCP client
Native remote MCP: use the URL directly (streamable HTTP, OAuth). Otherwise:
npx mcp-remote https://drop.neuronik.io/mcp. -
Say "drop this" — your assistant publishes the page and hands you back a URL.
What your assistant can do
| Tool | What it does |
|---|---|
publish_page | Publish a full HTML page, get a shareable URL |
update_page | Edit a page in place — same URL, refreshed preview |
list_pages | List the workspace's pages |
get_page | Fetch a page's HTML + metadata before editing |
delete_page | Delete a page |
Pages can be public (anyone with the link, with proper Open Graph previews on Discord/Slack/WhatsApp/X) or private (signed-in workspace members only, encrypted at rest).
drop-upload CLI
A remote MCP server can't read files on your machine. @neuronik/drop-upload (source) is the tiny local helper that bridges the gap — upload a screenshot, PDF or any file and get back an HTTPS URL your assistant can embed in a page:
npx @neuronik/drop-upload@latest ./screenshot.png
npx @neuronik/drop-upload@latest --clipboard # macOS: whatever image is on the clipboard
One-time setup: generate an upload token in drop under Connect assistant, then npx @neuronik/drop-upload@latest login --token <token>. Full docs in cli/README.md.
Feedback
Found a bug, want a feature, or built something cool with drop? Open an issue — we read everything.
License
The contents of this repository (CLI + docs) are MIT. The drop cloud service is © Neuronik.
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.