browse-mcp
Headless-browser MCP server for any MCP-capable agent (Claude, Codex, Gemini CLI, Cursor, ...). Playwright-based, with accessibility-tree refs, Readability, search, annotated screenshots, and a self-improvement feedback loop. Windows, Linux, and macOS.
Seal evidence
Auto-sealed Tier 1 on import from npm registry search. Lossy Channel layers 1–2 to be backfilled by the Foreman.
L1-wash
Pinned to 0.8.2
Similar tools
wayfinder
Local-first open-source browser agent with MCP server & visual workflows
noaa-climate-mcp-server
Search NOAA CDO stations and datasets, fetch historical weather observations via MCP. STDIO or Streamable HTTP.
agent-scrape
Pay-per-call web scraping for AI agents — no signup, no API keys, just USDC. x402-monetized MCP server on Base mainnet, deployed on Cloudflare Workers. 6 tools: scrape, extract (Groq + Llama 4), screenshot, metadata, workflow, session.
Scrapo
AI-native, agent-first web scraping for Python. Cost-aware tiered fetching (HTTP, browser, stealth, agent), model-agnostic LLM extraction with self-healing selector caches, API-first resolution, deterministic replay and field-level diff, and an MCP server.