Integrations · Claude Code

Add a web-scraping API to Claude Code. One command.

Remote MCP over HTTPS. Not an official Claude plugin, not an npx package. Paste the command, restart, ask a URL a question.

Claude Code talks to Plainscrape the same way Cursor does: HTTP MCP, header x-api-key. Firecrawl installs as a marketplace plugin or npx firecrawl-mcp. We don't. The server is already up.

The command

Claude Code
claude mcp add --transport http plainscrape \
  https://www.plainscrape.com/mcp \
  --header "x-api-key: ps_live_YOUR_KEY"

Restart Claude Code once. Then: “Use Plainscrape extract_page on this URL — title, price, rating. Confirm one record, not a list.”

Five tools, not six

The agent gets extract, extract_page, answer, get_results, and account. It does not get web search, domain map, or click-and-scroll. Site-wide extraction is capped: max_pages clamps at 10. That is a product clamp, not a timeout-safe crawl of a whole docs site.

Output is JSON. Markdown and CSV are on the docs roadmap.

FAQ

claude mcp add --transport http plainscrape https://www.plainscrape.com/mcp --header "x-api-key: ps_live_YOUR_KEY". Restart Claude Code. This is HTTP MCP, not an official Claude plugin.

Five, matching the REST API: extract, extract_page, answer, get_results, account. There is no web-search tool, no map tool, and no click/scroll browser API.

Yes for the extraction loop: the tool returns the structured answer, not the page. Large crawls are not the product — max_pages is clamped at 10.

Per successful page fetched. Failed pages are free. Same key and limits as REST. 100-page trial, 14 days, no card.

Get an API key.

Start the 100-page trial

14 days · no card · failed pages free · full MCP setup