Anybrowse
MCP-native web scraping and search API for AI agents. Converts any URL to clean Markdown with 90% success rate, including Cloudflare-protected sites and JS SPAs. Real-time web search via Brave Search API. CAPTCHA solving built-in. 10 free scrapes/day.
README
anybrowse
URL → Clean Markdown. For AI agents.
anybrowse.dev converts any URL to LLM-ready Markdown. Built for AI agents, MCP clients, and developers who need reliable web content extraction.
Why anybrowse?
- 84% scrape success rate — including Cloudflare-protected sites, JavaScript SPAs, government portals
- Real-time web search — powered by Brave Search API, not browser-based scraping
- MCP-native — works directly in Claude Code, Cursor, Windsurf with zero config
- Pay as you go — 10 free scrapes/day. Credit packs from $5. No subscription required.
- CAPTCHA solving — automatic reCAPTCHA and Cloudflare Turnstile solving
Quick Start
MCP (Claude Code, Cursor, Windsurf)
Add to your MCP config:
{
"mcpServers": {
"anybrowse": {
"type": "streamable-http",
"url": "https://anybrowse.dev/mcp"
}
}
}
Then ask your agent: "Scrape https://techcrunch.com and summarize the top stories"
REST API
curl -X POST https://anybrowse.dev/scrape \
-H "Content-Type: application/json" \
-d '{"url": "https://techcrunch.com"}'
Python SDK
pip install anybrowse
from anybrowse import AnybrowseClient
client = AnybrowseClient()
result = client.scrape("https://techcrunch.com")
print(result.markdown)
JavaScript/TypeScript
npm install anybrowse
import { AnybrowseClient } from 'anybrowse';
const client = new AnybrowseClient();
const result = await client.scrape('https://techcrunch.com');
Endpoints
| Endpoint | Description | Price |
|---|---|---|
| POST /scrape | URL → Markdown | $0.002/call |
| POST /crawl | Multi-page crawl | $0.01/call |
| POST /search | Web search → Markdown | $0.002/call |
| POST /extract | Structured data extraction | $0.01/call |
| POST /batch | Up to 10 URLs parallel | $0.002/URL |
Pricing
- Free: 10 scrapes/day, no API key needed
- Credit packs: $5 (3k scrapes) / $20 (15k scrapes) / $50 (50k scrapes)
- Pro: $4.99/month, unlimited
- x402: Pay per request with USDC on Base (AI agents with wallets)
Links
Tech
Node.js + TypeScript + Fastify + Playwright + SQLite. Deployed on VPS with pm2.
Open source under MIT license.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.