
NewsAgent Data
@newsagentdata
NewsAgent Data について
MCP server for the NewsAgent Data API — scored, classified Russian & English news intelligence for AI agents (Claude, Cursor, Cline).
基本情報
設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"newsagent": {
"command": "python",
"args": [
"/absolute/path/to/newsagent_mcp.py"
],
"env": {
"NEWSAGENT_API_KEY": "your_key_here"
}
}
}
}ツール
5Filtered feed — by country, topic, language, political lean, audience, min urgency, date range
Full-text keyword search across the archive
Recent high-urgency news (urgency ≥ 7 by default)
Live totals — articles, sources, countries, languages (no key)
Source catalog metadata (Standard tier+)
概要
What is NewsAgent Data?
NewsAgent Data is an MCP server that allows querying scored, classified Russian and English news from any MCP client (Claude Desktop, Cursor, Cline, etc.). It wraps the NewsAgent Data API, returning articles already scored for urgency (0–10), classified by political lean, topic, country, and audience, and de-duplicated.
How to use NewsAgent Data?
Obtain a free API key, install dependencies with pip install -r requirements.txt, and add the server configuration to your MCP client (e.g., claude_desktop_config.json) pointing at newsagent_mcp.py with the NEWSAGENT_API_KEY environment variable. After restarting the client, five tools appear automatically: get_feed, search_news, get_breaking, coverage_stats, and list_sources.
Key features of NewsAgent Data
- Pre-scored news urgency (0–10) and de-duplicated articles.
- Filter by country, topic, language, political lean, audience, and date range.
- Full-text keyword search across the news archive.
- Live coverage totals (articles, sources, countries, languages) without an API key.
- Breaking news feed with configurable urgency threshold (default ≥7).
- Source catalog metadata for Standard tier and above.
Use cases of NewsAgent Data
- Query breaking sanctions news from Russia with urgency 7 or higher.
- Search the archive for "central bank rate" in the last 14 days, English only.
- Compare how state vs. opposition sources covered Ukraine in a given week.
- Retrieve live coverage statistics – number of countries and sources covered.
FAQ from NewsAgent Data
What tools does NewsAgent Data expose?
Five tools: get_feed, search_news, get_breaking, coverage_stats, and list_sources. Each returns pre-scored and classified results.
What are the API key and tier requirements?
Free and Developer tiers have a history window (1–7 days) and daily quotas; the server surfaces 401/403/429 errors. The list_sources tool requires a Standard-tier key. Channel handles are never exposed.
Can I change the API host?
Yes, set the NEWSAGENT_API_BASE environment variable to override the default https://api.newsagentdata.com.
What data does the server return?
Articles are already scored for urgency (0–10), classified by political lean, topic, country, and audience, and de-duplicated – no additional NLP pipeline is needed.
How do I configure NewsAgent Data in Cursor or Cline?
Point the MCP server command at newsagent_mcp.py with NEWSAGENT_API_KEY in the environment, the same as for Claude Desktop.
「データと分析」の他のコンテンツ
Google Analytics MCP Server
surendranbGoogle Analytics 4 data to AI agents, agentic workflows, and MCP clients. Give agents analysis-ready access to website traffic, user behavior, and performance data with schema discovery, server-side aggregation, and safe defaults that reduce data wrangling.
Google Ads MCP
cohnenAn MCP tool that connects Google Ads with Claude AI/Cursor and others, allowing you to analyze your advertising data through natural language conversations. This integration gives you access to campaign information, performance metrics, keyword analytics, and ad management—all th
Data Visualization MCP Server
isaacwassermanPubMed Analysis MCP Server
DarkroasterA PubMed MCP server.
HubSpot MCP Server
baryhuangA Model Context Protocol (MCP) server that enables AI assistants to interact with HubSpot CRM data, providing built-in vector storage and caching mechanisms help overcome HubSpot API limitations while improving response times.
コメント