chatpipe-mcp
Publish live web pages from AI coding agents. Instant shareable URLs for dashboards, landing pages, and reports with password protection.
README
<p align="center"> <img src="https://chatpipe.net/chatpipe-logo-64.png" alt="ChatPipe" width="64" height="64" /> </p>
<h1 align="center">ChatPipe MCP Server</h1>
<p align="center"> <strong>Publish live web pages from your AI coding agent — instant shareable URLs from your terminal.</strong> </p>
<p align="center"> <a href="https://chatpipe.net">Website</a> · <a href="#quick-start">Quick Start</a> · <a href="#available-tools">Tools</a> · <a href="#pricing">Pricing</a> </p>
<p align="center"> <img src="demo.gif" alt="ChatPipe demo — describe, generate, publish" width="720" /> </p>
ChatPipe MCP is a Model Context Protocol server that lets AI coding agents publish HTML content as live, shareable web pages. Describe what you need — a dashboard, a landing page, a form — and get a public URL in seconds.
No deployment pipelines. No hosting configuration. No domain setup. Just describe and publish.
Features
- Instant publishing — HTML to live URL in under a second
- Global delivery — Pages load fast from anywhere in the world
- Access control — Public pages or password-protected with encryption
- Update in place — Modify published pages without changing the URL
- Works with any MCP client — Compatible with any AI coding agent that supports the Model Context Protocol
Quick Start
Prerequisites
- A free ChatPipe account
- An MCP-compatible AI coding agent
1. Generate an API key
Sign up at chatpipe.net, then navigate to Settings → API Key (MCP) → Generate API Key.
Note: Copy the key immediately after generation. It will not be shown again. You can regenerate a new key at any time, which revokes the previous one.
2. Install (one command)
Run this in your terminal — replace YOUR_API_KEY with the key from step 1:
claude mcp add chatpipe --transport url https://api.chatpipe.net/mcp --header "Authorization: Bearer YOUR_API_KEY"
That's it. Restart your AI coding agent and ChatPipe tools are ready.
<details> <summary>Manual setup (alternative)</summary>
If you prefer to configure manually, add this to your MCP client config file:
{
"mcpServers": {
"chatpipe": {
"type": "url",
"url": "https://api.chatpipe.net/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}
Replace YOUR_API_KEY with the key generated in step 1.
</details>
3. Start publishing
Try these prompts in your AI coding agent:
"Create a landing page for my project and publish it"
"Build a dashboard showing monthly revenue and publish it as a live page"
"Make a contact form and give me a shareable link"
Available Tools
publish_page
Publish HTML content as a live, shareable page. Returns a public URL.
| Parameter | Type | Required | Description |
|---|---|---|---|
name |
string |
Yes | Page title (e.g., "Monthly Dashboard") |
slug |
string |
Yes | URL slug, lowercase with hyphens (e.g., "monthly-dashboard") |
html |
string |
Yes | Complete HTML content to publish |
access |
string |
No | "public" (default) or "password" |
password |
string |
No | Required when access is "password" |
list_projects
List all published pages with their URLs, names, and access levels. Takes no parameters.
update_page
Update the HTML content of an existing page. The URL remains the same.
| Parameter | Type | Required | Description |
|---|---|---|---|
slug |
string |
Yes | Slug of the page to update |
html |
string |
Yes | New HTML content |
name |
string |
No | New page title |
delete_page
Permanently remove a published page.
| Parameter | Type | Required | Description |
|---|---|---|---|
slug |
string |
Yes | Slug of the page to delete |
Use Cases
| Who | What |
|---|---|
| Consultants | Build client dashboards and share a live URL in your next message |
| Developers | Publish project pages, docs, or demos without a deploy pipeline |
| Sales teams | Generate custom proposals as live pages for each prospect |
| Marketers | Spin up landing pages on the fly and test them immediately |
| Freelancers | Share deliverables as live pages instead of static files |
Pricing
| Free | Pro ($19/mo) | Business ($49/mo) | |
|---|---|---|---|
| Projects | 5 | Unlimited | Unlimited |
| Link expiry | 30 days | Never | Never |
| Password protection | — | Yes | Yes |
| Email-restricted access | — | — | Yes |
| Team seats | — | — | 5 |
Manage your plan at chatpipe.net.
Security
- All communication encrypted over HTTPS
- API keys scoped per user — each key can only access its owner's pages
- Keys can be regenerated at any time (revokes the previous key)
- Password-protected pages are encrypted at rest
Contributing
Found a bug or have a feature request? Open an issue.
Links
- ChatPipe — Create your account and manage projects
- Model Context Protocol — Learn about MCP
License
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.
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.
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.
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.