Scrapingant is an MCP server with 3 tools an agent can call, among them get_web_page_html, get_web_page_markdown, get_web_page_text. It answers at https://api.scrapingant.com/mcp/ over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 11 of 11 times since 5 September 2026; the last check, on 8 November 2026, succeeded.
Cloud-based web access with real browsers and JS rendering by ScrapingAnt
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
get_web_page_html | Fetch (scrape) a URL using ScrapingAnt and return the web page content as HTML. Args: url: The URL of the page to extract (scrape). browser: Whether to use browser rendering. Default: True. proxy_type: Type of proxy to use. Default: 'datace Inputs: url, browser, proxy_type, proxy_country |
get_web_page_markdown | Fetch (scrape) a URL using ScrapingAnt and return the web page content as Markdown. Args: url: The URL of the page to extract (scrape). browser: Whether to use browser rendering. Default: True. proxy_type: Type of proxy to use. Default: 'da Inputs: url, browser, proxy_type, proxy_country |
get_web_page_text | Fetch (scrape) a URL using ScrapingAnt and return the web page content as plain text. Args: url: The URL of the page to extract (scrape). browser: Whether to use browser rendering. Default: True. proxy_type: Type of proxy to use. Default: ' Inputs: url, browser, proxy_type, proxy_country |
Every block below points at https://api.scrapingant.com/mcp/. Pick your client and copy.
claude mcp add --transport http scrapingant https://api.scrapingant.com/mcp/
{
"mcpServers": {
"scrapingant": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://api.scrapingant.com/mcp/"]
}
}
}{
"mcpServers": {
"scrapingant": {
"url": "https://api.scrapingant.com/mcp/"
}
}
}{
"servers": {
"scrapingant": {
"type": "http",
"url": "https://api.scrapingant.com/mcp/"
}
}
}{
"context_servers": {
"scrapingant": {
"url": "https://api.scrapingant.com/mcp/"
}
}
}{
"mcpServers": {
"scrapingant": {
"serverUrl": "https://api.scrapingant.com/mcp/"
}
}
}{
"mcpServers": {
"scrapingant": {
"url": "https://api.scrapingant.com/mcp/"
}
}
}name: Scrapingant
version: 0.0.1
schema: v1
mcpServers:
- name: Scrapingant
type: streamable-http
url: https://api.scrapingant.com/mcp/{
"mcpServers": {
"scrapingant": {
"httpUrl": "https://api.scrapingant.com/mcp/"
}
}
}{
"mcpServers": {
"scrapingant": {
"type": "http",
"url": "https://api.scrapingant.com/mcp/"
}
}
}{
"mcpServers": {
"scrapingant": {
"url": "https://api.scrapingant.com/mcp/"
}
}
}goose://extension?url=https%3A%2F%2Fapi.scrapingant.com%2Fmcp%2F&type=streamable_http&id=scrapingant&name=Scrapingant
It answered our last check on 8 November 2026 in 21 ms. Over 11 checks since 5 September 2026 it answered 11. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by scrapingant.com and served from api.scrapingant.com, the vendor's own domain: https://api.scrapingant.com/mcp/.
3, as returned by the server's own tools/list on 31 August 2026: get_web_page_html, get_web_page_markdown, get_web_page_text.
It answered our last check on 8 November 2026 in 21 ms. Over 11 checks since 5 September 2026 it answered 11.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://api.scrapingant.com/mcp/. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: com.scrapingant. Endpoint host: api.scrapingant.com. ARD identifier: urn:air:com.scrapingant:mcp:mcp.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.