News MCP
Provides access to news articles from a PostgreSQL database and offers a tool to summarize them using the OpenAI API.
news-mcp MCP server
mcp news server
Components
Resources
The server exposes news articles stored in a database via a resource URI:
news://{category}/{limit}: Retrieves a list of the latest articles for a given category.{category}: Filters articles by category (e.g.,tech,data_science,news). See tool description for full list.{limit}(optional, default 10): Specifies the maximum number of articles to return.
- Each returned article includes title, link, published date, and source.
Prompts
The server currently does not expose any prompts. (The summarization logic exists internally but is not available via an MCP prompt).
Tools
The server implements one tool:
summarize_news: Retrieves raw news articles from the database, allowing the client (LLM) to summarize them.- Takes optional
category(string) andlimit(integer, default 20) arguments. - Returns a list of article dictionaries, each containing
id,title,link,published,source, andcontent. - Available categories:
tech,data_science,llm_tools,cybersecurity,linux,audio_dsp,startups,news,science,research,policy.
- Takes optional
Configuration
The server relies on a PostgreSQL database configured via the DATABASE_URL environment variable (defaults to postgresql://localhost/mcp_news).
The news_gatherer.py script (intended to be run separately/scheduled) populates the database from various RSS feeds.
Summarization logic (internal, not exposed via MCP) uses the OpenAI API, configured via the OPENAI_API_KEY environment variable.
Other configurations (via environment variables or defaults):
LOOKBACK_HOURS: How far backnews_gatherer.pylooks for new articles (default: 6).SUMMARY_WORD_TARGET: Target word count for internal summarization (default: 500).MAX_ARTICLES_PER_SUMMARY: Maximum articles included in one summary batch (default: 25).KEYWORD_FILTER: Keywords used by internal summarization logic.
Quickstart
Install
Claude Desktop
On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
Development/Unpublished Servers Configuration
``` "mcpServers": { "news-mcp": { "command": "uv", "args": [ "--directory", "~/dev/news-mcp", "run", "news-mcp" ] } } ```Published Servers Configuration
``` "mcpServers": { "news-mcp": { "command": "uvx", "args": [ "news-mcp" ] } } ```Development
Building and Publishing
To prepare the package for distribution:
- Sync dependencies and update lockfile:
uv sync
- Build package distributions:
uv build
This will create source and wheel distributions in the dist/ directory.
- Publish to PyPI:
uv publish
Note: You'll need to set PyPI credentials via environment variables or command flags:
- Token:
--tokenorUV_PUBLISH_TOKEN - Or username/password:
--username/UV_PUBLISH_USERNAMEand--password/UV_PUBLISH_PASSWORD
Debugging
Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.
You can launch the MCP Inspector via npm with this command:
npx @modelcontextprotocol/inspector uv --directory ~/dev/news-mcp run news-mcp
Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.
相关服务器
Cycling Coach AI
AI-powered cycling training coach: personalized training plans, daily workouts, nutrition, strength training, fitness metrics (FTP, VO2Max), and Strava, Garmin, Wahoo, MyWhoosh, and Rouvy integrations.
Hit The Road Rentals
Search motorhomes, RVs and campervans worldwide — instant results from 300+ rental companies across AU, NZ, US, CA, UK and more.
MCP-Ambari-API
Automate Apache Ambari operations with AI/LLM: Natural language commands for Hadoop cluster management, service control, configuration monitoring, and real-time status tracking via Model Context Protocol (MCP) tools.
Meelion MCP
Brazilian fixed income & financial data for AI - Selic, CDI, IPCA, CDB/LCI rankings and market quotes via JSON-RPC
MCP Server Market
A centralized repository for discovering and utilizing Model Context Protocol (MCP) servers.
Cast
MCP server for Google Cast — discover devices, play media, control volume, launch apps, and manage queues over stdio
Cinderfi
Tax-aware retirement planning for Canada and the US — CPP/OAS, Social Security, RRSP/TFSA/401k/IRA, Monte Carlo, withdrawal optimization.
Compound MCP Server
Lending and borrowing data, market rates, and user positions on Compound Finance.
Bazi
An MCP server for accessing Bazi (Chinese astrology) data, requiring an API key.
TradeMemory Protocol
AI trading memory layer for MT5/forex with 15 MCP tools — store/recall trades, pattern discovery, strategy evolution, and Outcome-Weighted Memory.