Pageree MCP Server

Build, publish, capture leads from, measure and improve landing pages — from your AI assistant.

Pageree is a hosted remote MCP server. Connect it to an MCP client and your assistant can design a landing page, host it on a real URL, collect form submissions, read visitor analytics, and revise the page against what the numbers show. There is nothing to install and no API key to paste: authentication is OAuth, handled in the browser by your client.

This repository is the public home of the Pageree MCP server: its documentation and its server.json registry manifest. The server itself is hosted by Pageree and its implementation is not open source, so there is no source tree here to build or run.

What it does

Pageree is built around one workflow — discover → build → publish → measure → improve — and the tools follow it.

Pages

Leads and goals

Form submissions from published pages are captured by Pageree and delivered to the destination you configure.

Analytics

Pageree injects its own first-party tracking into published pages and attributes behaviour to individual page sections, so an assistant can tell which part of a page is losing visitors rather than only that the page is.

Assets and media

Custom domains

Built-in guidance

A set of get_skill_* tools returns Pageree's own instructions to the assistant on demand — page structure and required markup, conversion copywriting, reading analytics, the optimisation loop, image handling, form management, custom domains, privacy and consent, and content policy. The assistant loads the relevant one before it works, so page-building guidance stays current without you maintaining local rules or skill files.

whoami reports the connected account; get_subprocessors returns the current subprocessor list.

Requirements

• An MCP client that supports remote servers over Streamable HTTP with OAuth — VS Code with GitHub Copilot, Claude, ChatGPT, Cursor, Codex, Claude Code, Gemini CLI, Windsurf, Cline, or OpenCode.
• A Pageree account.
• Network access to https://mcp.pageree.com/.

Service usage is subject to your Pageree plan.

Configure

VS Code (GitHub Copilot)

Add the server from the Command Palette — MCP: Add Server → HTTP — and enter https://mcp.pageree.com/. Or create .vscode/mcp.json in your workspace, merging with any servers already there:

{
  "servers": {
    "pageree": {
      "type": "http",
      "url": "https://mcp.pageree.com/"
    }
  }
}

Start the server, then complete the Pageree sign-in that opens in your browser and approve the access request. Pageree's tools become available in agent mode.

Other clients

Most clients take the same two values — the URL and the Streamable HTTP transport. The transport field differs by client: Gemini CLI uses httpUrl, VS Code uses "type": "http", and Cline uses "type": "streamableHttp".

{
  "mcpServers": {
    "pageree": {
      "url": "https://mcp.pageree.com/"
    }
  }
}

Per-client walkthroughs are at pageree.com/docs.

The endpoint ends at /. Do not append /mcp or /sse.

Verify the connection

In a new agent chat:

Use Pageree to call whoami and list_pages. Do not create, change, or publish anything.

You should see the connected account and its pages. An empty list is expected on a new account.

Use it

Build a page

Create a landing page for my accounting service with a quote-request form. Ask me about the business, the audience, and the action I want first, then show me a preview before publishing.

Capture the leads

Send new enquiries from this page to my email.

Improve it with real data

Review visitor engagement on my landing page, tell me which section is losing people, and propose one change. Wait for my approval before editing or publishing.

Publishing makes a page public. Review the preview and confirm the destination before asking an assistant to publish.

Troubleshooting

Repository contents

README.md            This document
server.json          MCP registry manifest for com.pageree/landing-pages
assets/logo.svg      Pageree logo

No executable code, server runtime, or credentials are distributed here. Tool calls go to the hosted Pageree service; your client stores its own OAuth credentials.

Links

• Setup documentation · VS Code guide
• Pageree dashboard
• Official MCP registry entry
• Privacy · Terms · Subprocessors
• Support: support@pageree.com