Crawl4Agent

com.saastemlyv1.0.1790881666Updated Oct 1, 2026

crawl4ai-compatible web crawler API: POST a URL, get clean LLM-ready Markdown with fit_markdown...

VerifiedStreamable HTTPWeb executableWeb Search & Scraping

Overview

AI-generated overview

Remote MCP server that crawls a URL and returns clean, LLM-ready Markdown for an assistant to read or summarize.

What it does
Crawl4Agent is a remote, crawl4ai-compatible web crawler exposed over streamable HTTP. It accepts a URL and returns cleaned page content as LLM-ready Markdown, including a fit_markdown form. It is aimed at turning web pages into text an assistant can work with directly.
When to use it
Use it when an assistant needs the readable text of a specific web page rather than raw HTML, for example to summarize, quote, or extract content from a link. It is a reasonable addition when page-to-Markdown conversion is a recurring need.
Requirements
A remote endpoint at crawl4agent.saastemly.com over streamable HTTP; no local package or runtime is needed. An Authorization header carrying a Bearer API key is used for prepaid credits; tools with a free tier work without one.
Before you install
The Authorization header carries a secret API key, so treat it as a credential and do not expose it. Paid use draws on prepaid credits purchased from the provider. Crawled page content is sent to a third-party service, so avoid submitting URLs with sensitive or private data.

Installation

In SourceWeft

  1. Open Crawl4Agent in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "crawl4agent": {
      "type": "http",
      "url": "https://crawl4agent.saastemly.com/mcp"
    }
  }
}

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v1.0.1790881666LatestOct 1, 2026