Lovable MCP Server
Enables AI assistants to programmatically generate Lovable Build URLs to create applications from prompts, with optional image references and structured requirements.
README
Lovable MCP Server
An MCP (Model Context Protocol) server for the Lovable Build with URL API. Generate shareable URLs that programmatically create applications in Lovable.
Overview
This server allows you to programmatically create and interact with Lovable applications by generating "Build with URL" links. By connecting this MCP server with an AI assistant (like Claude), the AI can build full, running applications from a simple text prompt.
Features & Tools
1. lovable_generate_build_url
Generate a shareable Lovable Build URL from a prompt and optional reference images.
Parameters:
prompt(string, required): Description of the app to build (max 50,000 chars)images(string[], optional): Up to 10 publicly accessible image URLs (JPEG/PNG/WebP)autosubmit(boolean, optional): Auto-start building when URL is opened (default:true)response_format("markdown" | "json"): Output format (default: "markdown")
2. lovable_validate_build_url
Validate and parse an existing Lovable Build URL, checking for issues.
Parameters:
url(string, required): The Lovable Build URL to validateresponse_format("markdown" | "json"): Output format (default: "markdown")
3. lovable_build_prompt
Compose an optimized prompt from structured requirements and return it as a Build URL.
Parameters:
app_type(string, required): Type of application (e.g., "todo app", "dashboard")features(string[], optional): Features to includestyle(string, optional): Visual style or themetech_preferences(string, optional): Technology preferencesadditional_context(string, optional): Additional requirementsresponse_format("markdown" | "json"): Output format (default: "markdown")
Setup & Installation
- Make sure you have Node.js and npm installed.
- Clone or download this repository.
- Install dependencies:
npm install
- Build the TypeScript code:
npm run build
Usage
Local Usage (stdio)
By default, the server runs using the stdio transport. This is ideal for local integrations, such as adding the server as an MCP to the Claude Desktop app.
npm start
Remote Usage (HTTP)
You can optionally run this server with an HTTP streaming transport on a given port.
TRANSPORT=http PORT=3000 npm start
Integration Guides
Claude Desktop Configuration
To add this server to the Claude desktop app, add the following to your claude_desktop_config.json:
{
"mcpServers": {
"lovable": {
"command": "node",
"args": ["/path/to/lovable-mcp-server/dist/index.js"]
}
}
}
Note: Replace /path/to/lovable-mcp-server/dist/index.js with the absolute path to your local built index.js.
Claude Code Configuration
If you're using the Claude Code CLI:
claude mcp add lovable node /path/to/lovable-mcp-server/dist/index.js
Examples
Generating a Build URL
Tool: lovable_generate_build_url
Input: { "prompt": "Create a todo app with categories and dark mode" }
Building from structured requirements
Tool: lovable_build_prompt
Input: {
"app_type": "dashboard",
"features": ["charts", "KPI cards", "data tables"],
"style": "modern",
"tech_preferences": "use shadcn/ui"
}
Validating an existing URL
Tool: lovable_validate_build_url
Input: { "url": "https://lovable.dev/?autosubmit=true#prompt=Create%20a%20todo%20app" }
License
MIT
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.