unulu

unulu

AI agent website builder, starting with link-in-bio sites. Create and publish via MCP server or REST API.

Category
Visit Server

README

<p align="center"> <img src="https://unulu.ai/unulu-logo-F.svg" alt="unulu" width="140" /> </p>

unulu

MCP Badge

AI agent website builder, starting with link-in-bio sites. Create and publish via MCP server or REST API.

v1.0 — Stable API.

What is unulu?

unulu is a website builder designed for AI agents. You describe a site in conversation with an AI assistant — Claude, ChatGPT, Gemini, Cursor, or any MCP-compatible tool — and it builds and publishes the site instantly.

Starting with link-in-bio sites: a single page with your name, bio, and links, live at yourhandle.unu.lu. No signup, no templates, no manual work.

What AI agents can do

  • Create a link-in-bio site with a name, bio, links, and theme
  • Read the current state of any site
  • Update content — display name, bio, links, theme, link badges
  • Check handle availability before claiming
  • 17 built-in themes including minimal, gradient, brutalist, glass, and more

Sites are published instantly and expire after 1 hour unless claimed with an email address.

Quick start (MCP)

Add unulu to your MCP client config:

{
  "mcpServers": {
    "unulu": {
      "type": "streamable-http",
      "url": "https://mcp.unulu.ai"
    }
  }
}

No authentication required. Then ask your AI agent: "Build a link-in-bio site for me on unulu."

REST API

Base URL: https://api.unulu.ai

Method Path Description
POST /api/sites Create a link-in-bio site
GET /api/sites/{site_id} Get site state
PATCH /api/sites/{site_id} Update a site
GET /api/claims/check-handle Check handle availability

No authentication required. Rate limited. Full spec: openapi.json

Example

See a live site at unulu.unu.lu.

Docs

Platform guides

Step-by-step setup for each AI platform:

Claude · ChatGPT · Gemini · Cursor · Copilot · Grok · Windsurf · Other

Roadmap

See open issues labeled enhancement for planned features. Suggestions welcome — open an issue.

Links

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured