Community Скиллы Веб-скрейпинг

Firecrawl для Cursor

Cursor
Открыть источник ↗ GitHub ↗
Установка 
git clone (см. README)

Описание

firecrawl-cursor-plugin — плагин Firecrawl для Cursor, приносящий веб-данные в агента: поиск — нахождение страниц по запросу, скрейпинг — извлечение чистого содержимого сайтов, взаимодействие — клики и заполнение форм на страницах, парсинг — превращение сырых страниц в структурированные данные. Для разработчиков на Cursor, которым нужен веб как источник данных для агента без написания собственных парсеров.

Что умеет:
— искать и скрейпить сайты;
— взаимодействовать со страницами;
— парсить контент в структуру;
— работать через hosted MCP-сервер.

Полная документация ниже — автоматически из репозитория firecrawl/firecrawl-cursor-plugin (ветка main). Оригинальные материалы проекта распространяются на условиях его лицензии.

Firecrawl Cursor Plugin

Generated from Firecrawl’s plugin source. Do not edit this repository by hand; changes made here are overwritten by the next sync.

Firecrawl is the context API for AI agents. This plugin connects your agent to the hosted Firecrawl MCP server to search the web, read pages, collect structured data, interact with live pages, and track changes.

What’s included

  • mcp.json: the hosted Firecrawl MCP server at https://mcp.firecrawl.dev/v2/mcp-oauth
  • skills/firecrawl: routes each request to the right Firecrawl tool (search, scrape, Alexandria data providers, agent, map and crawl, interact, parse, monitors, developer, paper and US government search), with a reference per operation
  • skills/firecrawl-deep-research: cited, multi-source investigations and comparisons
  • skills/get-started: checks the connection, finds a first goal and delivers a first result
  • Workflow skills: brand-identity (logo, colors and fonts for a document), business-contact-research (published business contacts), design (a site’s design system as DESIGN.md), enrich-lead (enrich supplied people or a lead CSV), fantasy-sports (start/sit, waiver and trade research), find-leads (ranked prospect lists), job-postings (current, verified openings), read-docs (answers from official documentation) and seo-audit (evidence-backed on-page SEO audit)

Setup

Install the plugin, then sign in to Firecrawl when Cursor asks (or open Customize, find the firecrawl MCP server and choose Authenticate). There is no API key to paste and nothing to install locally.

Capabilities

  • Search: web, news and image search with query-relevant excerpts, plus matching Alexandria data providers
  • Scrape: any URL to clean Markdown, JSON with a schema, a grounded answer or verbatim highlights
  • Alexandria: discover catalogued data providers and execute them for structured records
  • Agent: autonomous multi-source collection into structured data
  • Map and crawl: list a site’s URLs or collect a bounded section
  • Interact: clicks, forms and navigation in a live browser session
  • Parse: PDFs and documents, including local files through a hosted upload
  • Monitor: recurring checks for page changes
  • Developer, paper and US government search: issues, merged pull requests, READMEs and docs; published papers; statutes, regulations and court opinions