# News Sentiment API

Lets your agent pull sentiment history and growth for any keyword. Useful when you want to see how coverage tone shifted around a company or topic.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: trendsapi-ai
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/trendsapi-ai/news-sentiment-api
- Updated: 2026-08-18
- HTML: https://affpapa.org/en/nevibecode/mcp/news-sentiment-api

## What it does

The server sits in front of the Trends API and hands your agent two things: a sentiment time series and growth across a chosen window. No outlet scraping on your side — you get dated points on a 0-100 scale.

A `TRENDSAPI_KEY` is required, and a free one comes from trendsapi.ai. The Python client ships a sync `TrendsAPI` plus an async `AsyncTrendsAPI`, with `get_time_series`, `get_growth` and `get_top_trends`. Pass `source` in lowercase (`news sentiment`) and `type` exactly as the API spells it (`Google Trends`). Get the casing wrong or mix the two and the call comes back 400.

A negative `growth` value means tone dropped against the previous window. It does not mean the company itself is in bad shape. There are no per-article labels and no outlet breakdown, so don't expect the server to tell you which publication drove a move.

## Requirements
- Needs: Python and uv (commands run via uvx)
- Remote server: `https://news-sentiment.api.trendsapi.ai/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http news-sentiment-api https://news-sentiment.api.trendsapi.ai/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add news-sentiment-api --url https://news-sentiment.api.trendsapi.ai/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "news-sentiment-api": {
            "url": "https://news-sentiment.api.trendsapi.ai/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "news-sentiment-api": {
            "type": "http",
            "url": "https://news-sentiment.api.trendsapi.ai/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http news-sentiment-api https://news-sentiment.api.trendsapi.ai/mcp
```

## When to use it
- chart how news tone around a company moved over a year
- compare growth across several windows in one call
- load a sentiment series into pandas and average it by month
- query sentiment history from the agent instead of scraping outlets

## Example prompts
- Show me the news sentiment trend for nvidia over the last 12 months
- Pull growth for nvidia across the 3M and 12M windows
- Fetch the sentiment time series and average the values by month

## Similar
- [News Sentiment Trends MCP](https://affpapa.org/en/nevibecode/mcp/news-sentiment-trends-mcp.md) — MCP server · ★ 1
- [finance-sentiment](https://affpapa.org/en/nevibecode/skills/finance-sentiment.md) — skill · 1600 installs
- [okx-sentiment-tracker](https://affpapa.org/en/nevibecode/skills/okx-sentiment-tracker.md) — skill · 8100 installs
- [the-news](https://affpapa.org/en/nevibecode/skills/the-news.md) — skill · 17300 installs
- [news-monitor](https://affpapa.org/en/nevibecode/skills/news-monitor.md) — skill · 5100 installs
- [news-search](https://affpapa.org/en/nevibecode/skills/elvisun-news-search.md) — skill · 766 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md