
Anybrowse
Gives Claude three tools to fetch web content as clean Markdown using real Chrome browsers. The scrape tool converts any URL, handling JavaScript-heavy sites and PDFs. The crawl tool runs a Google search and scrapes the top results in one go. The search tool returns raw Google SERP data as JSON. Works immediately with 10 free calls per day, no API key required. Reaches 84% success rate on protected and dynamic sites where simpler scrapers fail. Built on streamable HTTP transport and supports x402 micropayments if you need higher volume.
- GitHub stars
- 3
- tools
- 3
- transport
- HTTP
- last updated
- Feb 20, 2026
Tools
3 toolsPublic tool metadata for what this MCP can expose to an agent.
scrapeConvert any URL to clean, LLM-optimized Markdown. Handles SPAs, dynamic content, and PDFs.
Convert any URL to clean, LLM-optimized Markdown. Handles SPAs, dynamic content, and PDFs.
No parameter schema in public metadata yet.
crawlSearch Google for a query and scrape the top results to Markdown.
Search Google for a query and scrape the top results to Markdown.
No parameter schema in public metadata yet.
searchGoogle search results as structured JSON (titles, URLs, snippets).
Google search results as structured JSON (titles, URLs, snippets).
No parameter schema in public metadata yet.
Sponsors
Readme
anybrowse
Convert any URL to clean, LLM-ready Markdown.
Real Chrome browsers with full JavaScript rendering. 84% success rate including JavaScript-heavy sites, Cloudflare-protected pages, and government sites.
🆓 10 free MCP calls/day — no signup required. Get 50/day free with email signup.
MCP Server (Free)
Connect any MCP-compatible client to https://anybrowse.dev/mcp (Streamable HTTP transport).
Quick config for Claude Desktop / Cline / Cursor:
{
"mcpServers": {
"anybrowse": {
"url": "https://anybrowse.dev/mcp"
}
}
}
No API key needed. Works out of the box. 10 free calls/day per IP, 50/day with a free account.
Tools
| Tool | Description |
|---|---|
scrape | Convert any URL to clean, LLM-optimized Markdown. Handles SPAs, dynamic content, and PDFs. |
crawl | Search Google for a query and scrape the top results to Markdown. |
search | Google search results as structured JSON (titles, URLs, snippets). |
HTTP API (x402 Pay-Per-Use)
Details
- Repository
- github.com/kc23go/anybrowse
- Categories
- Web & Browser Automation, AI & LLM Tools, Documents & Knowledge
- Transport
- HTTP
- Registry
- MCP registry, active