News Article Extractor

io.github.DataLeadsPROPublished by GitHub account DataLeadsPROv1.0.0Updated Nov 2, 2026

Extract clean article text, titles, and metadata from news URLs - ready for NLP pipelines.

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingData & Analytics

Overview

AI-generated overview

Remote MCP server that extracts clean article text, titles and metadata from news URLs for NLP pipelines.

What you can do
  • Extract article content from a news URL: returns clean body text, title and metadata via the news_article tool.
  • Handles page rendering and anti-bot protection server-side, so no proxies or scraping infrastructure are needed.
  • Output is aimed at downstream NLP and text-processing pipelines.
When to use it
Useful when an assistant needs readable article text from news pages for summarization, analysis or dataset building, especially when pages are protected or hard to scrape directly.
Requirements
Remote Streamable HTTP endpoint; no local runtime needed. A DataLeads client key is required (passed as clientKey in requests, or DATALEADS_API_KEY for the Docker stdio variant). Free tier available; paid tiers for higher volume.
Before you install
Requests consume a metered quota tied to a paid or free plan, so heavy use incurs cost. The client key is a credential and should be kept private. URLs submitted are sent to a third-party service that fetches the pages on your behalf.

Installation

In SourceWeft

  1. Open News Article Extractor 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.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.DataLeadsPRO%2Fnews-article-extractor/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "news-article-extractor": {
      "type": "http",
      "url": "https://data.dataleads.pro/mcp/news-article-extractor"
    }
  }
}

README

News Article Extractor API

Extract clean article text, titles, and metadata from news URLs - ready for NLP pipelines.

Part of the DataLeads API suite (News category). Requests render in a real browser with anti-bot handling and protected-page support built in - no proxies to manage, no infrastructure to run.

Endpoints

MethodPathDescription
POST/news/articleV1 News Article

Quick start

bash
curl -X POST https://data.dataleads.pro/v1/news/article \  -H 'Content-Type: application/json' \  -d '{"clientKey": "YOUR_CLIENT_KEY", "url": "https://www.bbc.com/news"}'

Replace YOUR_CLIENT_KEY with your key. Get one at https://data.dataleads.pro - free tier included.

MCP server

  • Remote (Streamable HTTP): https://data.dataleads.pro/mcp/news-article-extractor
  • Stdio (Docker): docker run -e DATALEADS_API_KEY=yourkey ghcr.io/dataleads/news-article-extractor-mcp:latest

Pricing

TierPriceRequests
Free$0500/mo
Starter$9/mo5,000
Pro$29/mo25,000
Business$99/mo100,000
Enterprisecustomcustom

Full plan details at https://data.dataleads.pro.

License

MIT - see LICENSE.

Source: README.md at commit 454720d

Tools

1

news_article

V1 News Article

ParametersurlmaxTimeout

Version history

1
  1. v1.0.0LatestSep 17, 2026

Score

90% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.