Back to MCP Servers
ScreensDesign MCP

ScreensDesign MCP

ScreensDesign MCP gives AI assistants access to mobile app design research: real app screens, complete onboarding and paywall flows, App Store reviews, market signals and saved collections. It is a hosted remote MCP server using Streamable HTTP and browser OAuth. A paid ScreensDesign Pro subscription is required. After adding the server, authenticate via /mcp in Claude Code. Setup: https://screensdesign.com/mcp/. Contact: ceo@screensdesign.com. The linked repository contains setup documentation, registry metadata and an optional companion skill, not the hosted server implementation.

SearchCloud

Install

claude mcp add --transport http screensdesign "https://api.screensdesign.com/v1/mcp" --scope user

claude_desktop_config.json

claude_desktop_config.json
{
  "mcpServers": {
    "screensdesign-mcp-n66s": {
      "command": "claude",
      "args": [
        "mcp",
        "add",
        "--transport",
        "http",
        "screensdesign",
        "\"https://api.screensdesign.com/v1/mcp\"",
        "--scope",
        "user"
      ]
    }
  }
}

Add this to your Claude Desktop config file. Find it at ~/Library/Application Support/Claude/claude_desktop_config.json on macOS.

What this does

ScreensDesign MCP exposes a set of tools to Claude over the Model Context Protocol. After you add it to claude_desktop_config.json (snippet above) and restart Claude Desktop, those tools become callable inside any conversation. That makes it useful when you want Claude to reach into search engines and knowledge bases without copy-pasting context every turn.

Common use cases

  • •Search the open web, internal docs, or a vector store from inside a Claude session
  • •Bring fresh information past Claude's training cutoff into context
  • •Run multi-source research without copy-pasting URLs and snippets