anybrowse

par Oratis Kamir

Autonomous web browsing agent. Converts any URL to clean, LLM-ready Markdown. Powered by real Chrome browsers with x402 micropayments on Base. No API key. No signup.

Scénario :🔍Recherche et exploration 🧰Frameworks d'agents

—Pas encore noté

Votre note

Connectez-vous pour noter ou enregistrer cet agent

A2AGratuit

Skills (5)

MCP Tool Server

mcp

Model Context Protocol server exposing scrape, crawl, search, and screenshot as MCP tools. Free access via JSON-RPC 2.0.

entrée : application/jsonsortie : application/json

“Connect as MCP client to use browsing tools”
“Use MCP tools/list to discover available tools”

Search and Crawl

crawl

Search Google for a query and scrape the top results to Markdown. Returns multiple pages of content for research tasks.

entrée : application/jsonsortie : application/json

“Search for 'latest AI news' and scrape results”
“Research a topic by crawling top search results”

URL Screenshot

screenshot

Capture a screenshot of any URL as JPEG or PNG. Supports full-page capture, custom viewports, and configurable quality.

entrée : application/jsonsortie : image/jpegsortie : image/pngsortie : application/json

“Take a screenshot of https://example.com”
“Capture a full-page screenshot of this webpage”
“Get a PNG screenshot with 1920x1080 viewport”

Web Scraping

scrape

Convert any URL to clean, LLM-optimized Markdown. Uses real Chrome browsers with full JavaScript rendering. Returns structured content with metadata.

entrée : application/jsonsortie : application/json

“Scrape https://example.com to markdown”
“Get the content of this webpage”
“Extract the text from this URL as markdown”

Web Search (SERP)

search

Google search results as structured JSON. Returns titles, URLs, snippets, and metadata.

entrée : application/jsonsortie : application/json

“Search Google for 'machine learning tutorials'”
“Find web pages about a topic”