article-scraper-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@article-scraper-mcp fetch article from https://example.com/news"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Article Scraper MCP
A Model Context Protocol (MCP) server that fetches article data from URLs using newspaper3k.
Features
Extract article title, text, author, and publication date
Robust error handling and URL validation
Structured data output
Built with FastMCP for easy integration
Related MCP server: Web Scraper MCP Server
Installation
Install directly from PyPI:
uvx article-scraper-mcpUsage
Add to your MCP client configuration:
{
"mcpServers": {
"article-scraper": {
"command": "uvx",
"args": ["article-scraper-mcp"]
}
}
}API
fetch_article(url: str) -> dict[str, Any]
Fetches and parses a news article from the given URL.
Parameters:
url: The URL of the news article to fetch
Returns: A dictionary containing:
title: Article titletext: Article content textauthor: Author name(s) (may be None)date: Publication date in ISO format (may be None)
Raises:
ValueError: If URL is invalid or article cannot be parsedrequests.RequestException: If HTTP request fails
Requirements
Python 3.11+
newspaper3k
requests
loguru
mcp[cli]
License
MIT
Available Tools
1 toolfetch_articleA
Fetch a news article by URL and return structured data.
Args:
url: The URL of the news article.
Returns:
A dict with keys: title, text, author, date.
Raises:
ValueError: If URL is invalid or article cannot be parsed.
requests.RequestException: If HTTP request fails.
Inputs: url (required). Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
Only one tool exists, so there is no possibility of confusion between tools. The purpose is singular and clear.
With only one tool, naming consistency is not an issue. The name 'fetch_article' follows a clear verb_noun pattern.
One tool is minimal for a server named 'article-scraper-mcp', which might imply more features like batch fetching or source listing. However, the tool is functional and well-defined, so it is borderline acceptable.
The single tool covers the core operation of fetching a structured article from a URL. Minor gaps exist, such as lack of support for multiple articles or error handling variations, but the basic use case is fully addressed.
Maintenance
Related MCP Connectors
Extract clean article text, titles, and metadata from news URLs - ready for NLP pipelines.
Full text, author, date and image for every news or blog link in a dataset, CSV or Google Sheet.
Fetch any RSS/Atom feed as clean JSON or extract article text from any URL. Built for AI agents.
Google News search and topics with the full article text in Markdown for LLMs.
Related MCP Servers
- AlicenseCqualityDmaintenanceEnables access to news from multiple sources including Google News and DuckDuckGo, supporting queries by location, category, site, date range, and providing top news headlines with detailed information.7MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to fetch, clean, and extract readable content from web pages, optionally including links and images, via the scrape_url tool.-
- FlicenseNot gradedqualityDmaintenanceEnables searching news articles and fetching top headlines via GNews API with filtering options.-

newspaper-mcpofficial
AlicenseNot gradedqualityCmaintenanceEnables LLM agents to discover news sources, list articles, parse and extract article text, search news, and perform NLP analysis such as keyword extraction and summarization.MIT