Article Scraper Mcp

@dmitriiweb

关于 Article Scraper Mcp

MCP to get an article text from an URL

#articles #news #scraping #parsing

基本信息

分类

浏览器自动化

许可证

MIT

运行时

python

传输方式

stdio

发布者

dmitriiweb

提交者

Dmitrii K

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "article-scraper": {
      "command": "uvx",
      "args": [
        "article-scraper-mcp"
      ]
    }
  }
}

工具

1

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.

概览

What is Article Scraper Mcp?

Article Scraper Mcp is a Model Context Protocol (MCP) server that fetches article data from URLs using the newspaper3k library. It extracts title, text, author, and publication date, providing structured output for use with MCP clients.

How to use Article Scraper Mcp?

Install the package from PyPI with uvx article-scraper-mcp. Add it to your MCP client’s configuration by including a server entry with the command uvx and arguments ["article-scraper-mcp"]. After configuration, invoke the fetch_article tool by passing a URL.

Key features of Article Scraper Mcp

Extracts article title, text, author, and publication date
Robust error handling with URL validation
Returns structured dictionary output
Built with FastMCP for easy MCP integration
Raises clear exceptions for invalid URLs or HTTP failures

Use cases of Article Scraper Mcp

—

FAQ from Article Scraper Mcp

How do I install Article Scraper Mcp?

Install directly from PyPI by running uvx article-scraper-mcp in your terminal.

What data does the `fetch_article` function return?

It returns a dictionary containing the article’s title, full text, author (may be None), and publication date (may be None, in ISO format).

What happens if the URL is invalid or the article cannot be parsed?

If the URL is invalid or parsing fails, the server raises a ValueError. If the HTTP request itself fails, it raises a requests.RequestException.

What are the system requirements for running Article Scraper Mcp?

Python 3.11 or higher is required, along with the packages newspaper3k, requests, loguru, and mcp[cli].

评论

浏览器自动化分类下的更多 MCP 服务器

Fetch

modelcontextprotocol

Model Context Protocol Servers

MCP server w/ Browser Use

FastAPI server implementing MCP protocol Browser automation via browser-use library.

Browser Control MCP

MCP server paired with a browser extension that enables AI agents to control the user's browser.

fetch-mcp

An MCP server for fetching URLs / Youtube video transcript.

Webpage Screenshot MCP Server

An MCP that gives your agent the ability to snap a screenshot of webpages. Useful when you want your agent to check its progress during development.