Headline Vibes
STDIOSentiment analysis server for news headlines with natural language date parsing
Sentiment analysis server for news headlines with natural language date parsing
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).
"yesterday", "last Friday", etc.)structuredContentnpm install npm run build
{ "mcpServers": { "headline-vibes": { "command": "node", "args": ["/absolute/path/headline-vibes/build/index.mjs"], "env": { "NEWS_API_KEY": "your-eventregistry-key", "TRANSPORT": "stdio" } } } }
TRANSPORT=http, HOST=0.0.0.0, PORT=<port>, and optionally ALLOWED_HOSTS/ALLOWED_ORIGINS.analyze_headlinesDaily sentiment snapshot for a single day. Arguments: { "input": string }.
YYYY-MM-DD.analyze_monthly_headlinesMonthly aggregation between two months. Arguments: { "startMonth": "YYYY-MM", "endMonth": "YYYY-MM" }.
JSON schemas powering structured results live in src/schemas/headlines.ts.
npm run watchNEWS_API_KEY=... npm run start:stdioTRANSPORT=http HOST=0.0.0.0 PORT=8787 NEWS_API_KEY=... npm run start:httpnode ./build/scripts/smoke.mjs 2025-02-01npm testTRANSPORT, HOST, PORT, NEWS_API_KEY, optional ALLOWED_HOSTS, ALLOWED_ORIGINS, LOG_LEVEL).npm run build) or via Railway’s build step.npm run start.GET /healthz returns 200 ok.See docs/railway.md for the full playbook.
MIT