Headline Vibes Analysis
Analyzes the sentiment of news headlines from major US publications using the NewsAPI.
Headline Vibes — EventRegistry MCP Server
Headline Vibes is a Model Context Protocol server that analyzes investor sentiment in US news headlines fetched from EventRegistry (newsapi.ai). It supports daily and monthly analysis modes, produces structured outputs with diagnostics, and runs over stdio or HTTP (Railway-ready).
Features
- Curated US newsroom coverage with investor relevance filtering
- Dual sentiment scores (general + investor) normalized to a 0–10 scale
- Political-leaning breakdowns, source distributions, and sampling diagnostics
- Natural-language date parsing for daily requests (
"yesterday","last Friday", etc.) - Structured JSON outputs compatible with MCP
structuredContent - Built-in token budgeting and rate-limit telemetry
Prerequisites
- Node.js v18+ (LTS recommended)
- EventRegistry API key (https://newsapi.ai)
Setup
- Install dependencies and build:
npm install npm run build - Configure environment variables (stdio example):
{ "mcpServers": { "headline-vibes": { "command": "node", "args": ["/absolute/path/headline-vibes/build/index.mjs"], "env": { "NEWS_API_KEY": "your-eventregistry-key", "TRANSPORT": "stdio" } } } } - For HTTP (Railway) deployments, set
TRANSPORT=http,HOST=0.0.0.0,PORT=<port>, and optionallyALLOWED_HOSTS/ALLOWED_ORIGINS.
Available Tools
analyze_headlines
Daily sentiment snapshot for a single day. Arguments: { "input": string }.
- Accepts natural language or
YYYY-MM-DD. - Returns investor/general scores, synopses, distributions, sample headlines, and diagnostics.
analyze_monthly_headlines
Monthly aggregation between two months. Arguments: { "startMonth": "YYYY-MM", "endMonth": "YYYY-MM" }.
- Outputs per-month political sentiments, headline counts, and token/sampling diagnostics.
JSON schemas powering structured results live in src/schemas/headlines.ts.
Development & Testing
- Watch mode:
npm run watch - Stdio run:
NEWS_API_KEY=... npm run start:stdio - HTTP run:
TRANSPORT=http HOST=0.0.0.0 PORT=8787 NEWS_API_KEY=... npm run start:http - Smoke check EventRegistry connectivity:
node ./build/scripts/smoke.mjs 2025-02-01 - Unit tests (Vitest):
npm test
Railway Deployment
- Set environment variables (
TRANSPORT,HOST,PORT,NEWS_API_KEY, optionalALLOWED_HOSTS,ALLOWED_ORIGINS,LOG_LEVEL). - Build once locally (
npm run build) or via Railway’s build step. - Start with
npm run start. - Health probe:
GET /healthzreturns200 ok.
See docs/railway.md for the full playbook.
License
MIT
Serveurs connexes
Bright Data
sponsorDiscover, extract, and interact with the web - one interface powering automated access across the public internet.
Influship Influencer Marketing MCP
AI Influencer Search, Creator Data, & Live Scraping
Bilibili
Interact with the Bilibili video website, enabling actions like searching for videos, retrieving video information, and accessing user data.
just-every/mcp-screenshot-website-fast
High-quality screenshot capture optimized for Claude Vision API. Automatically tiles full pages into 1072x1072 chunks (1.15 megapixels) with configurable viewports and wait strategies for dynamic content.
Socialcrawl MCP
Single API key to access 21 + real time social media data
Kakuyomu MCP Server
An MCP server for the Kakuyomu novel posting site, enabling users to search for works, retrieve episode lists, and read content.
ScrapeGraph AI
AI-powered web scraping using the ScrapeGraph AI API. Requires an API key.
BrowserCat MCP Server
Remote browser automation using the BrowserCat API.
anybrowse
Convert any URL to LLM-ready Markdown via real Chrome browsers. 3 tools: scrape, crawl, search. Free via MCP, pay-per-use via x402.
Plain Markdown
Convert any URL to clean, LLM-ready Markdown
Crawl4AI
Web scraping skill for Claude AI. Crawl websites, extract structured data with CSS/LLM strategies, handle dynamic JavaScript content. Built on crawl4ai with complete SDK reference, example scripts, and tests.