global-news-intelligence-mcp
Provides access to Ars Technica's RSS feed, enabling retrieval of technology news through the aggregated news service.
Provides access to Hugging Face's blog RSS feed, enabling retrieval of AI and machine learning news.
Provides access to NASA's release feed, enabling retrieval of space and science news.
Provides access to OpenAI's blog RSS feed, enabling retrieval of AI news.
Provides access to TechCrunch's RSS feed, enabling retrieval of technology and startup news.
Provides access to The Guardian's RSS feed, enabling retrieval of international news.
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., "@global-news-intelligence-mcp what are the top AI news stories right now?"
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.
Why This Exists
LLMs are only as good as their information. This MCP server gives your AI agent real-time access to curated, ranked, and summarized global news — with technology and AI coverage prioritized.
It is not a simple RSS reader. Every article passes through a pipeline:
RSS Fetch → Parse → Classify → Rank by Importance → Summarize → JSON ResponseBuilt for XiaoZhi AI but compatible with any MCP client (Claude Desktop, Codex, Continue, Cursor, etc.).
Related MCP server: NewsIQ MCP
Features
16 dedicated MCP tools — one per news category, plus headline and summary tools
28 RSS sources across technology, AI, hardware, open source, international, politics, finance, military, space, energy, entertainment, and domestic (China)
Smart ranking — articles scored by source credibility, keyword relevance, and recency
SQLite cache — 15-minute TTL eliminates redundant fetches; survives network outages
Proxy support — configurable HTTP/HTTPS proxy for mainland China environments
Fault isolation — a single failing source never crashes the server; degrades gracefully to cache
Zero API keys — works entirely on public RSS feeds, no registration required
Cross-platform — Windows, Linux, macOS; Python 3.10+
Quick Start
git clone https://github.com/ashtondebug/global-news-intelligence-mcp.git
cd global-news-intelligence-mcp
python -m venv .venv
source .venv/bin/activate # macOS/Linux
# .venv\Scripts\activate # Windows
pip install -e .
cp config.example.yaml config.yamlEnvironment Check
python check_env.pyGlobal News Intelligence MCP - Environment Check
Python 3.12.13: OK
fastmcp: OK httpx: OK feedparser: OK
pyyaml: OK pydantic: OK
Result: ALL CHECKS PASSEDStart
python -m global_news_mcpThe server listens on stdio. Connect it to your MCP client.
MCP Tools
Tool | Description |
| Top global headlines (tech/AI prioritized) |
| News by category with configurable limit |
| AI, chips, software, hardware, open source |
| Artificial intelligence |
| CPUs, GPUs, semiconductors, devices |
| Open source community and developer ecosystem |
| Space missions, science, technology |
| Global events from BBC, Reuters, Guardian |
| Political coverage |
| Markets, economy, business |
| Defense and security |
| Composite: international + politics + finance + military |
| China news (People s Daily, China News, NetEase, IT Home, 36Kr) |
| Oil, gas, renewables, energy policy |
| Entertainment industry |
| Summary for a specific article URL |
Response Format
[
{
"title": "OpenAI Announces GPT-5",
"source": "TechCrunch",
"time": "2026-08-04T10:30:00+00:00",
"summary": "OpenAI has officially announced GPT-5, their next-generation...",
"url": "https://techcrunch.com/2026/08/04/...",
"category": "ai"
}
]Up to 10 articles per response, ranked by importance.
Configuration
config.yaml (copy from config.example.yaml):
network:
timeout: 15
proxy:
enabled: false # Set to true for mainland China
http: "" # e.g. http://127.0.0.1:7890 (Clash)
https: "" # e.g. http://127.0.0.1:7890
cache:
ttl: 900 # Seconds (15 min)
logging:
level: "INFO"
file: "" # Empty = stderr only
sources:
technology: true # Toggle individual categories
ai: true
# ... 12 categories totalCommon proxy ports: Clash 7890 · V2Ray 10809 · SSR 1080
Architecture
┌──────────────────────────────────────┐
│ MCP Client (LLM) │
│ XiaoZhi AI / Claude / Codex / ... │
└──────────────────┬───────────────────┘
│ stdio (JSON-RPC)
┌──────────────────▼───────────────────┐
│ main.py (FastMCP) │
│ 16 registered tools │
└──┬───────┬──────┬───────┬────────────┘
│ │ │ │
▼ ▼ ▼ ▼
┌──────┐ ┌────┐ ┌──────┐ ┌──────────┐
│ rss │ │cache│ │ranking│ │summarizer│
│ .py │ │ .py │ │ .py │ │ .py │
└──┬───┘ └──┬─┘ └──┬───┘ └────┬─────┘
│ │ │ │
▼ ▼ ▼ ▼
┌──────┐ ┌──────┐ ┌──────┐ ┌──────────┐
│parser│ │SQLite│ │sources│ │classifier│
│ .py │ │ DB │ │ .py │ │ .py │
└──────┘ └──────┘ └──────┘ └──────────┘Pipeline: Sources → Fetch → Parse → Classify → Rank → Summarize → Return
News Sources
Category | Sources |
Technology | The Verge, TechCrunch, Ars Technica, MIT Technology Review |
AI | OpenAI Blog, DeepMind Blog, Hugging Face Blog |
Hardware | Tom s Hardware, AnandTech |
Open Source | Hacker News |
International | BBC News, Reuters World, The Guardian |
Politics | BBC Politics |
Finance | Reuters Business, CNBC |
Military | Defense News |
Space | Space.com, SpaceNews, NASA Releases, ESA Space Science |
Energy | OilPrice |
Entertainment | Variety |
Domestic (China) | People s Daily, China News, NetEase News, IT Home, 36Kr |
28 feeds total. To add a source, edit src/global_news_mcp/sources.py:
{"name": "My Source", "url": "https://example.com/rss", "category": "technology"},Client Integration
Claude Desktop
{
"mcpServers": {
"global_news": {
"command": "python",
"args": ["-m", "global_news_mcp"],
"cwd": "/path/to/global-news-intelligence-mcp"
}
}
}Codex / Continue / Cursor
Same pattern — point the command to your Python and set cwd to the project root.
Development
pip install -e ".[dev]"
pytestCode Conventions
loggingonly — neverprint()(stdout is JSON-RPC)pathlibfor all filesystem pathsUTF-8 throughout
Every
@mcp.tool()function must have a complete docstring
Adding a New Tool
@mcp.tool()
async def get_my_category_news() -> str:
"""Get news for my custom category."""
return await _fetch_news(["my_category"], 10)Project Structure
.
├── pyproject.toml
├── config.example.yaml
├── README.md
├── RUNBOOK.md
├── check_env.py
├── install.bat
├── start.bat
├── src/global_news_mcp/
│ ├── main.py # Entry point + 16 tool registrations
│ ├── sources.py # 28 RSS feed definitions
│ ├── rss.py # Async concurrent fetching
│ ├── parser.py # feedparser → Article model
│ ├── classifier.py # Keyword-based classification
│ ├── ranking.py # Importance scoring
│ ├── summarizer.py # Response formatting
│ ├── cache.py # SQLite cache layer
│ ├── network.py # httpx client (proxy/timeout)
│ ├── config.py # YAML config loader
│ └── logger.py # stderr logging
└── .gitignoreLicense
MIT © 2026
Available Tools
16 toolsget_ai_newsA
Get the latest artificial intelligence news.
Inputs: no named parameters. Returns: result
get_domestic_newsB
Get domestic China news from Chinese sources.
Inputs: no named parameters. Returns: result
get_energy_newsA
Get energy sector news: oil, gas, renewables, policy.
Inputs: no named parameters. Returns: result
get_entertainment_newsA
Get entertainment industry news.
Inputs: no named parameters. Returns: result
get_finance_newsA
Get finance and business news: stocks, economy, markets.
Inputs: no named parameters. Returns: result
get_hardware_newsA
Get hardware news: CPUs, GPUs, chips, semiconductors, devices.
Inputs: no named parameters. Returns: result
get_international_newsB
Get major international news from global sources.
Inputs: no named parameters. Returns: result
get_military_newsB
Get military and defense news.
Inputs: no named parameters. Returns: result
get_newsA
Get news by category. Use when the user asks for a specific domain. category: all, ai, technology, hardware, opensource, international, politics, finance, military, space_science, energy, entertainment, domestic.
Inputs: limit, category. Returns: result
get_news_summaryB
Get a summary of a specific article by URL.
Inputs: article_url (required). Returns: result
get_opensource_newsA
Get open source and developer community news.
Inputs: no named parameters. Returns: result
get_politics_newsB
Get political news.
Inputs: no named parameters. Returns: result
get_space_newsA
Get space and aerospace news: missions, science, technology.
Inputs: no named parameters. Returns: result
get_technology_newsA
Get technology news: AI, chips, software, hardware, open source.
Inputs: no named parameters. Returns: result
get_top_newsA
Get the most important global news right now. Tech/AI prioritized.
Inputs: no named parameters. Returns: result
get_world_newsB
Get major world news: international, politics, finance, military.
Inputs: no named parameters. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 16 tools
The generic get_news tool accepts a category parameter covering all specialized categories, making get_technology_news, get_ai_news, and others redundant. Additionally, get_world_news overlaps with get_international_news, get_politics_news, get_finance_news, and get_military_news, creating significant boundary ambiguity.
All tools follow a consistent 'get_' verb prefix with descriptive nouns (e.g., get_finance_news, get_top_news). Even get_news_summary fits the pattern of 'get' + noun phrase, and no naming conventions are mixed.
With 16 tools, the server is heavy, and the count is inflated by unnecessary category-specific variants that duplicate the functionality of get_news with a category parameter. The server could be reduced to get_news, get_top_news, and get_news_summary while maintaining full coverage, making the current count excessive.
The tool set covers the core news workflow: fetching by category, getting top news, and retrieving article summaries. However, it lacks search functionality and filtering by date/source, which are common in news intelligence, leaving minor gaps.
Maintenance
Related MCP Connectors
AI tool directory MCP server, live since July 2026. Tools, agents, models, companies, services.
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.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Hosted MCP server for live public-data APIs and Skills for AI agents.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceAn MCP server that fetches RSS feeds and shares them with LLMs, allowing AI assistants to access and present the latest news and articles from configured feeds.19-
- FlicenseNot gradedqualityDmaintenanceAn AI-powered news aggregator MCP server that fetches live news from multiple sources, provides AI summaries via Claude, and performs sentiment analysis and trending topic detection.-
- AlicenseNot gradedqualityDmaintenanceMCP server that fetches and filters AI-related news from 20+ RSS feeds with scheduled notifications and email digests.1MIT
- FlicenseNot gradedqualityDmaintenanceLocal MCP server that ingests and normalizes recent AI, tech, and research news from multiple sources, exposing tools for media agents to query and retrieve article content on demand.-