Skip to content
gentic.news — AI News Intelligence Platform
Connecting to the Living Graph…

Listen to today's AI briefing

Daily podcast — 5 min, AI-narrated summary of top stories

Lovable interface showing export option for an app as an MCP server with a database and API endpoint icon

Lovable Now Exports Any App as an MCP Server — Here's How to Use It with

Lovable now exports any app as an MCP server. Add the URL to Claude Code's claude.json for instant live data access — no manual API wiring required.

·1d ago·3 min read··17 views·AI-Generated·Report error
Share:
Source: news.google.comvia lovable_blog_gnMulti-Source
How do I publish my Lovable app as an MCP server and connect it to Claude Code?

Lovable's new feature publishes any app built on its platform as an MCP server. Add the server URL to your Claude Code `claude.json` to let Claude read, query, and act on your app's data in real time during development.

TL;DR

Lovable lets you publish your app as an MCP server, giving Claude Code direct access to your app's data and actions.

Key Takeaways

  • Lovable now exports any app as an MCP server.
  • Add the URL to Claude Code's claude.json for instant live data access — no manual API wiring required.

What Changed

Lovable apps move inside ChatGPT and Claude , Claude Code ...

Lovable, the AI-powered app builder, now lets you publish any app you build on its platform as an MCP server. This means the app you've been building — with its database, API endpoints, and business logic — can become a tool that Claude Code can call directly.

The feature is live now in Lovable's deployment settings. No additional coding or protocol knowledge required.

What It Means For You

If you build apps with Lovable, you've been able to ship full-stack applications with a prompt. But those apps were silos — you had to manually wire up APIs or export data to use them with other AI tools.

Now, with one click, your Lovable app becomes an MCP server. Claude Code can:

  • Query your app's database directly (users, orders, content)
  • Trigger actions (send emails, update records, run workflows)
  • Read real-time state during development and debugging

This is a huge time saver. Instead of building a separate API layer or writing export scripts, you get a standardized protocol interface that Claude Code speaks natively.

Try It Now

Step 1: Publish your Lovable app as an MCP server

  1. Open your app in Lovable
  2. Go to Settings > Deployments
  3. Enable Publish as MCP Server
  4. Copy the MCP server URL (looks like https://your-app.lovable.app/mcp)

Step 2: Connect to Claude Code

Add the server to your Claude Code configuration:

// claude.json
{
  "mcpServers": {
    "lovable-app": {
      "url": "https://your-app.lovable.app/mcp"
    }
  }
}

Step 3: Use it in Claude Code

Now when you're working in Claude Code, you can say things like:

"Read the latest 5 orders from my app's database and summarize them"

"Update the user with email 'test@example.com' to have role 'admin'"

"What's the current state of the shopping cart for user ID 42?"

Claude Code will call your app's MCP server, execute the query or action, and return results directly in your terminal.

Why This Matters

MCP is spreading fast. As of July 2026, Google Cloud, AWS Open Data, and Directus all support MCP. Lovable joining this ecosystem means the apps you build are no longer isolated — they become composable tools in your AI development workflow.

This is especially powerful for:

  • Rapid prototyping: Spin up a Lovable app, publish as MCP, and immediately use it in Claude Code to build features on top
  • Debugging: Have Claude Code query your app's live state to diagnose issues
  • Data pipelines: Use your app as a data source for Claude Code to analyze, transform, or report on

One Caveat

This feature is currently limited to apps deployed on Lovable's platform. If you've exported your app to your own infrastructure, you'll need to set up MCP manually. But for Lovable-hosted apps, this is a zero-config win.


Source: news.google.com

Source: gentic.news · · author= · citation.json

AI-assisted reporting. Generated by gentic.news from multiple verified sources, fact-checked against the Living Graph of 4,300+ entities. Edited by Ala SMITH.

Following this story?

Get a weekly digest with AI predictions, trends, and analysis — free.

AI Analysis

Claude Code users should immediately check if their Lovable apps can be published as MCP servers. This eliminates the need to build custom API endpoints or write data export scripts. Instead of asking Claude Code to 'read my database', you can now say 'read my app's data' — and it just works. The biggest workflow change: stop treating your Lovable apps as finished products. Think of them as live data sources that Claude Code can query during development. For example, if you're building a dashboard in Claude Code, you can have it pull live data from your Lovable app's MCP server rather than working with stale mock data. To get started: enable the feature on any existing Lovable app today. Add the URL to your `claude.json`. Then test a simple query like 'list all records in my users table'. Once you see how fast it is, you'll start building with this integration as a first-class part of your workflow.

Mentioned in this article

Enjoyed this article?
Share:

AI Toolslive

Five one-click lenses on this article. Cached for 24h.

Pick a tool above to generate an instant lens on this article.

Related Articles

From the lab

The framework underneath this story

Every article on this site sits on top of one engine and one framework — both built by the lab.

More in Products & Launches

View all