645 Model Context Protocol servers — searchable, rated, ready to install.
35+ web scraping tools. Firecrawl, Bright Data, Jina, Olostep, ScrapeGraph, Notte, Riveter.
Universal web scraper with LLM-ready markdown, RAG chunking, PDF/DOCX support.
300+ on-device MCP tools for macOS — local AI, voice, vision, browser automation, system control.
Trust-aware repository facts for agents: build, test, docs, license, and security, no scraping.
Render HTML, CSS, SVG, and Canvas animations to MP4 locally via Playwright/Chromium and FFmpeg.
Lets Claude Code or Codex CLI drive your real Chrome — sessions intact, 28 browser tools.
Capture, inspect & debug HTTPS traffic across iOS, Android, browsers & backends — 304 MCP tools.
Plain-English browser tests for AI agents: real Chrome, deterministic verdicts. Free, no API keys.
Route EVM transactions to browser wallets (MetaMask, etc.) for signing via EIP-6963
Structured web intelligence for AI agents. 5x fewer tokens than Playwright/Firecrawl, 84.7% accuracy
MCP server + Chrome extension for AI browser control with real sessions.
Web scraping MCP — extract clean markdown, links, and metadata from any URL.
Human-to-AI code review bridge. Review UI in the browser, AI agents fix code via MCP.
AI-powered web scraping and data extraction capabilities through ScrapeGraph API
Pay-per-call agent APIs over x402: web scraping, token compression, and semantic cache.
caniuse MCP — browser feature support tables
Firecrawl MCP — wraps the Firecrawl API (firecrawl.dev) for web
Native Swift macOS automation — 143 tools: AX, EventKit, voice, browser DOM, undo.
Deterministic UI extraction and screenshot diffing for AI coding agents.
Code-aware browser testing agent — 13 Playwright tools for AI code editors via MCP
Browser tasks, sessions, and recipes for MCP and HTTP automation.
EarScribe is a browser-based transcription tool that converts audio to text on-device using OpenAI
Give any LLM its own computer — Docker sandboxes with bash, browser, docs, and sub-agents
WordCast is a browser-based text-to-speech reader that runs entirely on-device using the Web Speech
POST /mcp