analyze_headlinesLABSCO SUMMARY
A number with the sample it came from attached.
Both tools return source distributions, political-leaning breakdowns and sample headlines next to the score, so you can see whether a reading rests on ten articles or a thousand. It reads US newsrooms only — treat it as a US-market signal rather than a global one.
What it is
A Node server over EventRegistry. It samples curated US newsrooms, filters for investor relevance, and returns two sentiment scores on a 0-10 scale with the sampling diagnostics behind them.
What you get
- A single day's sentiment snapshot, taking a plain date or natural language such as yesterday or last Friday — analyze_headlines
- Months aggregated between a start month and an end month — analyze_monthly_headlines
- Two scores per result, general and investor, normalised to a 0-10 scale
- Political-leaning breakdowns, source distributions and sample headlines alongside the score
- Structured JSON compatible with MCP structuredContent, plus token budgeting and rate-limit telemetry
Requirements
Node.js v18 or later and an EventRegistry API key in NEWS_API_KEY. Build with npm install and npm run build, then run build/index.mjs with TRANSPORT=stdio. For HTTP, set TRANSPORT=http with HOST and PORT, and optionally ALLOWED_HOSTS and ALLOWED_ORIGINS; a GET on /healthz returns 200 ok.
Setup effort
Build from source — git clone https://github.com/fred-em/headline-vibes.git
USE CASES
01
Reading the mood on a particular day
Ask for yesterday or a specific date and get investor and general scores back with the headlines that produced them.
02
Seeing whether a shift is real or a bad sample
The diagnostics travel with the score — how many articles, from which sources, leaning which way — so a spike can be checked rather than believed.
03
Looking at a trend rather than a day
Aggregate between two months and get per-month sentiment with headline counts, which smooths the single-day noise.
04
Feeding the score into something else
Results come back as structured JSON, so the number is usable by a downstream tool rather than only readable in the chat.
2 tools
Listed in project docs. Your client may show a different list.
analyze_monthly_headlinesBEFORE YOU INSTALL
What to know first
Tools you get
2 tools named in the project's documentation.
Requires
- node on PATH
- Node.js v18 or later
- NEWS_API_KEY in your environment
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
You clone and build this one yourself.
Server setup
TERMINAL
git clone https://github.com/fred-em/headline-vibes.git
cd headline-vibes
npm install
npm run buildMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"headline-vibes": {
"command": "node",
"args": [
"<YOUR_ABSOLUTE_PATH>/headline-vibes/build/index.mjs"
],
"env": {
"NEWS_API_KEY": "<YOUR_NEWS_API_KEY>",
"TRANSPORT": "stdio"
}
}
}
}
