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
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
claude mcp add --transport http --scope user screenrove https://screenrove.com/mcpStart a new session afterwards. Pickers open in your browser.
Cursor
Or add {"mcpServers":{"screenrove":{"url":"https://screenrove.com/mcp"}}} to ~/.cursor/mcp.json.
VS Code
code --add-mcp '{"name":"screenrove","type":"http","url":"https://screenrove.com/mcp"}'Codex
codex mcp add screenrove --url https://screenrove.com/mcpWindsurf / Devin
devin mcp add -s user screenrove https://screenrove.com/mcpCascade: add {"mcpServers":{"screenrove":{"serverUrl":"https://screenrove.com/mcp"}}} to ~/.config/devin/mcp_config.json.
ChatGPT
Turn on Settings → Security and login → Developer mode, open chatgpt.com/plugins, press + and use the MCP server URL below.
Anything else
https://screenrove.com/mcpStreamable HTTP. No key or account.
How it works
- Ask for a reference. “Find me some pricing page references and let me pick one.”
- 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.
- Build from it. Your agent gets the screenshot, notes on what the screen does, the measured design guide and a build prompt.
Try asking
- “Check my onboarding against real products on Screenrove.”
- “Show me three onboarding flows on Screenrove and let me pick one for my signup.”
- “What does Stripe’s pricing page look like? Build our pricing page with a similar structure.”
- “Get Linear’s design guide and use its product palette for our settings screen.”
Tools
build_handoff | Build an agent handoff prompt |
check_my_ui | Check the user's UI against real references |
get_design | Get a product's design guide |
get_product | Get one product |
get_screen | Get one screen |
get_screen_image | Get a screen's screenshot |
list_products | List captured products |
pick_reference | Let the user pick a reference |
search_screens | Search screens |
wait_for_pick | Wait 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.