anybrowse MCP Server (io.github.kc23go/anybrowse)

Converts any URL into clean, LLM-ready Markdown by using real Chrome browsers with full JavaScript rendering. The server is an MCP server with toolCount set to 5, exposed via https://anybrowse.dev/mcp using a Streamable HTTP transport.

🛠️ Key Features

Converts any URL to clean, LLM-ready Markdown
Uses real Chrome browsers with full JavaScript rendering
Targets JavaScript-heavy, Cloudflare-protected, and government sites (84% success rate stated)

🚀 Use Cases

Prepare web page content as Markdown for LLM consumption
Handle pages that require JavaScript rendering
Access content behind common web protections (as described)

⚡ Developer Benefits

Connect MCP-compatible clients to https://anybrowse.dev/mcp
Streamable HTTP transport for integration
Operates as an MCP server with 5 tools (toolCount)

⚠️ Limitations

Success rate is stated as 84%, indicating non-universal retrieval
Free usage is limited: 10 free MCP calls/day without signup (50/day with email signup)

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:

json

{
  "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)

Endpoint	Price	Description
`POST /scrape`	$0.003 USDC	URL → Markdown
`POST /crawl`	$0.005 USDC	Search + scrape top results
`POST /serp/search`	$0.002 USDC	Google SERP as JSON

Example

bash

curl -X POST https://anybrowse.dev/scrape \
  -H "Content-Type: application/json" \
  -H "X-PAYMENT: <x402_payment_proof>" \
  -d '{"url": "https://example.com"}'

Response:

json

{
  "url": "https://example.com",
  "title": "Example Domain",
  "markdown": "# Example Domain\n\nThis domain is for use in illustrative examples...",
  "status": "ok"
}

Free Tier

Tier	Limit	How to get it
Anonymous	10 MCP calls/day	Just use it — no config needed
Free account	50 calls/day	Sign up — 10 seconds, no credit card
Credits	3,000+ calls	Buy credits from $5
x402	Unlimited	Pay per call with USDC on Base

Payment

Payments use the x402 protocol with USDC on Base. Any x402-compatible client or agent wallet can pay automatically. The facilitator is Coinbase CDP (https://api.cdp.coinbase.com/platform/v2/x402).

Discovery

Agent card: https://anybrowse.dev/.well-known/agent-card.json
OpenAPI spec: https://anybrowse.dev/openapi.json
x402 discovery: https://anybrowse.dev/.well-known/x402
Health: https://anybrowse.dev/health

urls	array	required	List of URLs to scrape (max 10)
context	string	optional	Optional: what you're trying to accomplish

url	string	required	The URL to extract data from
schema	object	required	Field names mapped to type strings. Format: {"fieldName": "string\|number\|boolean\|array\|object"}. Example: {"title": "string", "price": "number", "inStock": "boolean", "tags": "array"}
context	string	optional	Optional: what you're trying to accomplish (helps LLM extraction accuracy)

url	string	required	The URL to scrape (must start with http:// or https://)
context	string	optional	Optional: what you're trying to accomplish (e.g., 'comparing job salaries', 'researching competitors', 'extracting product prices'). Helps anybrowse return more relevant content.

q	string	required	The search query
count	number	optional	Number of results to scrape (1-20, default 3)
context	string	optional	Optional: what you're trying to accomplish (e.g., 'finding competitors pricing', 'researching market trends'). Helps return more targeted results.

q	string	required	The search query
count	number	optional	Number of results (1-20, default 5)
context	string	optional	Optional: what you're trying to accomplish. Helps with result relevance.

io.github.kc23go/anybrowse

anybrowse MCP Server (io.github.kc23go/anybrowse)

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

batch_scrape

extract

scrape

crawl

search

anybrowse

MCP Server (Free)

Tools

HTTP API (x402 Pay-Per-Use)

Example

Free Tier

Payment

Discovery

Links

Install

Remote endpoint

Related servers