screenroveSCREENS WORTH STUDYING
For agents

Give your agent real screens to build from.

Screenrove is an MCP server. Connect it once and your coding agent can search 159 captured screens from Linear, Vercel, Airbnb, Stripe, Duolingo, Notion, Raycast, Cal.com, Framer and Supabase, show you a few to choose from, and build from the one you pick.

Connect

Claude

claude.ai, Claude Desktop and mobile
Add to Claude

Opens claude.ai with Screenrove filled in as a custom connector. It then works in Desktop and mobile too, and the picker shows right in the chat.

Claude Code

Terminal
claude mcp add --transport http --scope user screenrove https://screenrove.com/mcp

Start a new session afterwards. Pickers open in your browser.

Cursor

One click
Add to Cursor

Or add {"mcpServers":{"screenrove":{"url":"https://screenrove.com/mcp"}}} to ~/.cursor/mcp.json.

VS Code

GitHub Copilot agent mode
Add to VS Code
code --add-mcp '{"name":"screenrove","type":"http","url":"https://screenrove.com/mcp"}'

Codex

CLI, IDE extension and ChatGPT desktop
codex mcp add screenrove --url https://screenrove.com/mcp

Windsurf / Devin

Devin Desktop and CLI
devin mcp add -s user screenrove https://screenrove.com/mcp

Cascade: add {"mcpServers":{"screenrove":{"serverUrl":"https://screenrove.com/mcp"}}} to ~/.config/devin/mcp_config.json.

ChatGPT

Developer mode

Turn on Settings → Security and login → Developer mode, open chatgpt.com/plugins, press + and use the MCP server URL below.

Anything else

Any MCP client
https://screenrove.com/mcp

Streamable HTTP. No key or account.

How it works

  1. Ask for a reference. “Find me some pricing page references and let me pick one.”
  2. Pick in your browser. Your agent opens a page with a few real screens side by side. Hover to scroll a long page, click the one you want. In Claude and ChatGPT the picker can appear right in the chat.
  3. Build from it. Your agent gets the screenshot, notes on what the screen does, the measured design guide and a build prompt.

Try asking

Tools

build_handoffBuild an agent handoff prompt
check_my_uiCheck the user's UI against real references
get_designGet a product's design guide
get_productGet one product
get_screenGet one screen
get_screen_imageGet a screen's screenshot
list_productsList captured products
pick_referenceLet the user pick a reference
search_screensSearch screens
wait_for_pickWait for the user's pick

Prefer HTTP?

Everything is also a REST API. See the OpenAPI spec or llms.txt. Usage is recorded anonymously, as described in our privacy notes.