drop
Publishes HTML pages straight from your AI assistant to a shareable URL, then lets you manage them - update, list, search, fetch, and delete pages in a public or private workspace. Turns "share what I just made" into a single tool call from Claude, Cursor, or any MCP client.
README
<p align="center"> <a href="https://drop.neuronik.io"> <img src="https://drop.neuronik.io/og.png" alt="drop — your AI writes the page, drop gives it a link" width="640"> </a> </p>
<h1 align="center">drop</h1>
<p align="center"> <strong>Publish web pages straight from your AI assistant — and share them with a link.</strong><br> <a href="https://drop.neuronik.io">drop.neuronik.io</a> · MCP-native · works with Claude, Cursor & any MCP client </p>
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/mcp<details><summary><strong>Claude Code</strong></summary>
claude mcp add --transport http drop https://drop.neuronik.io/mcpThen run
/mcp, select drop, and complete the browser sign-in. </details><details><summary><strong>Claude Desktop / Claude.ai</strong></summary>
Settings → Connectors → Add custom connector → paste the URL → Connect → sign in with Google. </details>
<details><summary><strong>Cursor</strong></summary>
Settings → MCP → Add new MCP server, or use:
{ "mcpServers": { "drop": { "command": "npx", "args": ["mcp-remote", "https://drop.neuronik.io/mcp"] } } }</details>
<details><summary><strong>Any other MCP client</strong></summary>
Native remote MCP: use the URL directly (streamable HTTP, OAuth). Otherwise:
npx mcp-remote https://drop.neuronik.io/mcp. </details> -
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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.