Provides news search capabilities on Google News by keyword, topic, site, or location, returning discovered articles to the agent.
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., "@newspaper-mcp Search Google News for 'artificial intelligence' and summarize the top article."
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.
An MCP server that exposes newspaper4k's news article discovery and extraction capabilities as tools for LLM agents. Built with the official MCP Python SDK v2.
Tool | Description |
| Download and parse a single article (title, authors, text, images, NLP). |
| Download and parse multiple article URLs concurrently. |
| Crawl a news site's homepage for brand info, categories, feeds, articles. |
| List article URLs/titles discovered on a source, with pagination. |
| Search Google News by keyword/topic/site/location (requires |
| Fast text-only extraction from raw HTML or a URL, no metadata/NLP. |
| Download + run NLP: keywords with scores and an extractive summary. |
| List a source's section/category URLs. |
| List a source's RSS/Atom feed URLs. |
Related MCP server: News Aggregator MCP Server
This package depends on the local newspaper4k checkout at the repository
root (via tool.uv.sources in pyproject.toml), so it always uses the
in-development version of the library.
cd newspaper_mcp
uv syncuv run newspaper-mcp # stdio transport (default)
uv run mcp dev src/newspaper_mcp/server.py # MCP InspectorTo add it to an MCP host (e.g. Claude Code, Claude Desktop), point the host
at uv run --directory /path/to/newspaper_mcp newspaper-mcp as a stdio
server.
search_news requires the optional gnews package, already pulled in via
the newspaper4k[gnews] extra declared in pyproject.toml.
NLP features (nlp(), keyword extraction, summarization) require nltk,
pulled in via the newspaper4k[nlp] extra. On first use, nltk may need
to download its punkt tokenizer data.
All tools perform live network requests to the target news sites; there is no caching between calls.
This server cannot be deployed
Web data for agents: YouTube transcripts, screenshots, Google News, WHOIS, jobs, tech stack, more.
Google News search and topics with the full article text in Markdown for LLMs.
Real-time corroborated news events + 5-year archive, for agents. Free tier, no key.
The only News based AI MCP your agents will ever need — custom categories, global regions, and time-scoped results in one tool. We use multi-vector & sparse-hybrid search to search through thousands of articles across the world to find the exact news you're looking for.
