Web Content Extract Mcp is a remote MCP server that gives an AI agent 5 tools, among them extract_article, fetch_url_content, get_page_links. It answers at https://web-content-extract-mcp.mcpize.run/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 1 of 6 times since 11 September 2026; the last check, on 24 October 2026, succeeded.
Web Content Extract Mcp connects AI agents to real public APIs via MCP. Tools include
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
extract_article | Extract main article content from a news/blog URL. Returns: {title, description, body, author, date} Inputs: url |
fetch_url_content | Fetch and extract clean text content from a public URL. Returns: {title, text, url, word_count} Inputs: url, max_chars |
get_page_links | Extract all links from a page. Returns: {links: [href], internal_count, external_count} Inputs: url, same_domain_only |
get_page_metadata | Get metadata from a page: title, description, og tags, keywords. Returns: {title, description, keywords, og_title, og_image, og_type} Inputs: url |
health_check | Server health check. |
Every block below points at https://web-content-extract-mcp.mcpize.run/mcp. Pick your client and copy.
claude mcp add --transport http web-content-extract-mcp https://web-content-extract-mcp.mcpize.run/mcp
{
"mcpServers": {
"web-content-extract-mcp": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://web-content-extract-mcp.mcpize.run/mcp"]
}
}
}{
"mcpServers": {
"web-content-extract-mcp": {
"url": "https://web-content-extract-mcp.mcpize.run/mcp"
}
}
}{
"servers": {
"web-content-extract-mcp": {
"type": "http",
"url": "https://web-content-extract-mcp.mcpize.run/mcp"
}
}
}{
"context_servers": {
"web-content-extract-mcp": {
"url": "https://web-content-extract-mcp.mcpize.run/mcp"
}
}
}{
"mcpServers": {
"web-content-extract-mcp": {
"serverUrl": "https://web-content-extract-mcp.mcpize.run/mcp"
}
}
}{
"mcpServers": {
"web-content-extract-mcp": {
"url": "https://web-content-extract-mcp.mcpize.run/mcp"
}
}
}name: Web Content Extract Mcp
version: 0.0.1
schema: v1
mcpServers:
- name: Web Content Extract Mcp
type: streamable-http
url: https://web-content-extract-mcp.mcpize.run/mcp{
"mcpServers": {
"web-content-extract-mcp": {
"httpUrl": "https://web-content-extract-mcp.mcpize.run/mcp"
}
}
}{
"mcpServers": {
"web-content-extract-mcp": {
"type": "http",
"url": "https://web-content-extract-mcp.mcpize.run/mcp"
}
}
}{
"mcpServers": {
"web-content-extract-mcp": {
"url": "https://web-content-extract-mcp.mcpize.run/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fweb-content-extract-mcp.mcpize.run%2Fmcp&type=streamable_http&id=web-content-extract-mcp&name=Web%20Content%20Extract%20Mcp
It answered our last check on 24 October 2026 in 250 ms. Over 6 checks since 11 September 2026 it answered 1. Status here comes from Neuronto's own probes, not from the publisher.
5, as returned by the server's own tools/list on 25 October 2026: extract_article, fetch_url_content, get_page_links, get_page_metadata, health_check.
It answered our last check on 24 October 2026 in 250 ms. Over 6 checks since 11 September 2026 it answered 1.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://web-content-extract-mcp.mcpize.run/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: io.github.varvararatta. Endpoint host: web-content-extract-mcp.mcpize.run. ARD identifier: urn:air:io.github.varvararatta:mcp:web_content_extract_mcp.
First indexed 10 September 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.