Веб-скрейпинг и браузер

MCP server for screenshots, PDFs, OG images, and narrated video recording from Claude Desktop, Cursor, and Windsurf

Record any browser page as GIF or video. AI-driven demo recording with scroll/click/hover interactions via Playwright + ffmpeg

Compresses ~100K-token HTML into 2-5K-token structured maps while preserving every actionable element. AI agents can read and interact with any web page at 97% fewer tokens

Free webpage screenshot capture API with format, viewport, and dark mode options. No API key required

Non-custodial paying-fetch client for agents that pay APIs over HTTP 402 (x402, USDC on Base). The operator sets hard per-call/per-day/per-host spend caps, an approval threshold, and allow/deny lists, with an append-only receipt for every attempt; the agent can't raise its own limits. @forum-labs/payfetch payfetch-mcp

Free HTML/URL to PDF conversion API powered by Playwright. No API key required

Website & web-app testing built for AI agents rather than raw browser bindings: 66 Playwright tools with hard assertions, auto form-fill, persistent authenticated sessions (incl. interactive login for 2FA/SSO), network mocking, real INP, and accessibility/SEO/GEO (llms.txt, AI-crawler access, WebMCP) + Lighthouse…

7 tools for French open-data building permits (Sitadel, 311k rows, ~2M permits/year, Etalab license). Search, details, DVF transactions cross-ref, real estate dealer opportunity score, PLU urban zoning, BRGM natural and technological risks, and a Vue 360 composite that fans out 6 sub-fetches in one tool call. Powered…

UK planning application data for AI agents: search planning applications by council, postcode, keyword, status, type, or date range; find applications near a lat/lng point; fetch a specific application; and list supported councils. Requires a PlanWire API key

An MCP server using Playwright for browser automation and webscrapping

An MCP python server using Playwright for browser automation,more suitable for llm

Search the Podcast Index: podcasts, episodes, guest appearances by person, trending shows, and feed health

Record what you do on any website and securely automate it forever. Replays browser actions in headless Playwright with encrypted credentials and AI-powered selector healing

Local MCP adapter/server for browser-only image workflows. Resize, compress, convert, remove backgrounds, strip metadata, watermark and export image packs through QuokkaPix without uploading source images to a processing server

MCP server + Chrome extension that gives AI agents control of the user's real browser with existing sessions, logins, and cookies. No headless browser, no re-authentication

Screenshot, PDF, and HTML rendering API for AI agents. Capture any URL or raw HTML as PNG/JPEG/WebP/PDF with batch processing, geo-targeting, async webhooks, and MCP-native integration. Free tier included

MCP server for authenticated REST API calls — auto-login, token caching, 2FA/OTP support, Swagger spec fetch, and fuzzy endpoint search. Works with any REST API without writing auth code

RSS feeds MCP server with 8 tools — fetch, filter, search, and manage RSS feeds by category or source. Zero config, no API keys required

Native Safari browser automation for AI agents with 80+ tools. No Chrome dependency, optimized for Apple Silicon with 60% less CPU overhead

MCP server for ScraperAPI web scraping with JavaScript rendering, geotargeting, premium proxies, and auto-parsing support

Fetch any web page's HTML (or AI-parsed JSON, or Google results) through the ScrapeUnblocker anti-bot API (Cloudflare, DataDome, PerimeterX, Akamai, Shape), using your own API key. Three tools: fetch_html , fetch_parsed , google_search

Screaming Frog SEO Spider headless crawls, data export, and technical SEO audit skill for Claude. 8 tools, cross-platform (Mac + Windows), includes a ready-to-use technical SEO scan skill

A Model Context Protocol server providing web automation capabilities through Selenium WebDriver

MCP server bridging Claude Desktop with Selenix for browser automation and testing. Create, run, debug, and manage browser tests through natural language