Let your AI agent write your app's landing and policies

Your coding agent already knows your app. It has read the code that decides whether you use analytics, which sign-in providers you support and whether ads or AI services receive user data. Those are exactly the questions a privacy policy depends on. Lanpage's MCP server lets that agent answer them for you and draft the pages your app needs.

What MCP is, briefly

The Model Context Protocol is an open standard that lets AI clients, such as Claude Code, claude.ai, Cursor or VS Code, use tools from outside services. Lanpage exposes its own tools through an MCP server, so the agent can read and edit your Lanpage drafts from the same conversation where it works on your code.

Connect it once

With Claude Code, one command adds the server:

claude mcp add --transport http lanpage https://lanpage.co/api/mcp

Cursor, VS Code, claude.ai and other clients use the same address. The MCP page has the exact setup for each one, including a bridge for clients that only run local servers.

The first time, your browser opens. You sign in to Lanpage and approve what the client may do. There is no API key to copy or leak, and you can disconnect the client at any time from your account.

What the agent can do

• Answer the app facts from your repository. Accounts, analytics, ads, payments and AI use. The agent reads package.json, the Podfile, build.gradle, the Android manifest and the code. Lanpage includes a ready-made prompt for this called fill_app_facts.
• Draft your documents. Privacy Policy, Terms, support and account deletion pages, plus custom pages, based on those facts.
• Build the landing. Blocks, theme, FAQ, store links, logo and screenshots. If the app is already on the App Store, it can import the icon and screenshots from the listing.
• Tell you what is missing. The agent reads the store checklist and reports what still blocks a submission.

A typical request looks like this:

Set up my app in Lanpage. Fill in the app facts from this repo, draft the privacy policy and the account deletion page, and build a landing with the App Store screenshots. Tell me what the checklist still needs.

What stops it from acting on its own

Handing an agent access to public pages deserves some care, so the server is built around a few limits:

• Everything it writes is a draft. Your live site only changes when you publish.
• You confirm the changes that matter. Publishing, unpublishing, deleting and changing an address wait for your answer, in the client or through a one-time link. The model cannot confirm on your behalf.
• It works inside your account and your plan. Ownership and plan limits are checked on every call, the same as in the dashboard.
• Some things stay out of reach. The agent never sees the email addresses your landing collected, your billing or how to close your account.
• You can see what it did. Your account lists every connected client and every change an agent made.

On which plan

Reading and drafting work on every plan, Free included, so you can have the agent prepare everything and publish from the dashboard. Publishing from the agent itself is part of Pro. See pricing for the details.

Why this saves time

The slow part of writing a privacy policy is remembering every SDK the app uses. The agent does not have to remember: it reads the code. When you add a new SDK later, ask it to check the facts again and update the draft, and you review the change before it goes live.

Lanpage is not a law firm, and the documents remain yours to review. The agent gets you a complete first draft in minutes instead of an afternoon. Create your free account, connect your agent and ask it to set up your app.