MCP server that fetches article data (title, text, author, date) from a URL using newspaper3k
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"article-scraper-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# 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 ## Installation Install directly from PyPI: ```bash uvx article-scraper-mcp ``` ## Usage Add to your MCP client configuration: ```json { "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 title - `text`: Article content text - `author`: 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 parsed - `requests.RequestException`: If HTTP request fails ## Requirements - Python 3.11+ - newspaper3k - requests - loguru - mcp[cli] ## License MIT
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.