# NewsMCP - News Search (`newsmcp/news`) Actor

Search live world news deduplicated into story events, with corroboration counts and source links. One dataset item per story.

- **URL**: https://apify.com/newsmcp/news.md
- **Developed by:** [NewsMCP](https://apify.com/newsmcp) (community)
- **Stats:** 3 total users, 2 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

Pay per usage

This Actor is paid per platform usage. The Actor is free to use, and you only pay for the Apify platform usage, which gets cheaper the higher subscription plan you have.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-usage

## What's an Apify Actor?

Actors are web data automations that power AI and operations. They run on the Apify platform to scrape websites, process data, connect APIs, and automate workflows.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.
Actors are written with capital "A".

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.
The best way to integrate Actors is as follows.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — the [REST API](https://docs.apify.com/api/v2.md).

For usage examples, see the [API](#api) section below.

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).

# README

## NewsMCP — News Search

### What does NewsMCP News Search do?

**NewsMCP News Search** returns **live world news deduplicated into story events** — one dataset item per real-world story rather than hundreds of near-identical articles. Each story carries a headline, abstract, key actors, industry and event-type labels, **corroboration counts** (how many independent newsrooms carried it, separate from syndicated reprints), and links to original sources. Learn more at [newsmcp.com](https://newsmcp.com).

### Why use it?

- **Deduplicated stories, not article noise** — hundreds of reprints collapse into one story event with a corroboration count.
- **Verification built in** — the `newsrooms` field counts outlets that reported independently, mirrors excluded.
- **Integration-ready** — one JSON dataset item per story, usable from Make, n8n, Zapier, schedules, and the API.

### How to use it

1. Optionally enter a **Query** (keywords) or a **Subject** (one company, person, or place).
2. Optionally narrow by event type, sector, content type, minimum newsrooms, or date.
3. Run. Each matching story lands in the dataset as one item. You can download the dataset in formats such as JSON, CSV, or Excel.

Running with no input at all returns the most-corroborated stories of the last 24 hours.

### Output

One dataset item per story event:

```json
{
    "event_id": "evt_68a39482537d58170c374a0ec880684b",
    "headline": "Cargo Plane Crashes at Miami Airport",
    "abstract": "A Boeing 767 cargo plane crashed at Miami International Airport...",
    "entities": [{ "name": "Miami International Airport", "salience": 0.9 }],
    "event_type": "accidents_disasters.transport_accident",
    "content_type": "news_report",
    "sector": "transport_logistics",
    "newsrooms": 835,
    "reports": 1205,
    "source_count": 1628,
    "language_count": 41,
    "mirror_ratio": 0.53,
    "first_seen": "2026-09-06T18:33:35",
    "last_seen": "2026-09-08T12:50:35",
    "sources": ["https://www.nytimes.com/..."]
}
```

### Event type values

Use exact `family.leaf` values, comma-separated for OR: corporate\_finance.earnings\_report, corporate\_finance.analyst\_rating, corporate\_finance.dividends, markets.stock\_move, markets.commodity\_price, markets.currency\_move, deals.merger\_acquisition, deals.ipo\_filing, deals.asset\_sale, governance.board\_change, governance.shareholder\_vote, governance.executive\_departure, society\_environment.climate\_event, society\_environment.public\_health, society\_environment.environmental\_incident, sports.match\_result, sports.transfer\_signing, sports.championship, justice\_crime.arrest\_charge, justice\_crime.trial\_verdict, justice\_crime.investigation, security.cyberattack, security.data\_breach, security.physical\_security\_incident, macro\_policy.central\_bank\_decision, macro\_policy.trade\_policy, macro\_policy.fiscal\_policy, research\_science.scientific\_discovery, research\_science.clinical\_trial\_result, research\_science.publication, religion\_society.religious\_event, religion\_society.social\_movement, politics.election, politics.policy\_announcement, politics.diplomacy, legal\_regulatory.regulatory\_action, legal\_regulatory.lawsuit\_filed, legal\_regulatory.compliance\_ruling, culture\_media.celebrity\_news, culture\_media.entertainment\_release, culture\_media.award, product.product\_launch, product.product\_recall, product.feature\_update, accidents\_disasters.natural\_disaster, accidents\_disasters.industrial\_accident, accidents\_disasters.transport\_accident, operations.plant\_closure, operations.layoffs, operations.supply\_chain\_disruption, funding.venture\_funding\_round, funding.grant\_award, local\_civic.local\_government\_action, local\_civic.infrastructure\_project, geopolitics.armed\_conflict, geopolitics.sanctions, geopolitics.diplomacy\_summit, corporate\_comms.press\_release, corporate\_comms.leadership\_statement, unclassifiable.

### Sector values

government\_public\_sector, media\_entertainment, financial\_services, healthcare\_pharma, energy\_utilities, retail\_consumer, real\_estate, agriculture\_food, telecommunications, automotive, manufacturing\_industrial, transport\_logistics, aerospace\_defense, mining\_metals, construction\_infrastructure, education, hospitality\_travel, sports\_recreation, nonprofit\_ngo, legal\_services, insurance, software\_it\_services, ecommerce, banking, defense\_security, chemicals, fashion\_apparel, gaming\_esports, biotechnology, semiconductors, other\_sector.

### Pricing

Priced to be effectively free — a tiny fee per story stored in the dataset. A typical run costs a fraction of a cent.

### Related Actors

- [get-story](https://apify.com/newsmcp/get-story) — full detail of one story, including its complete source list.
- [check-coverage](https://apify.com/newsmcp/check-coverage) — how widely and independently a claim was reported.
- [newsmcp-server](https://apify.com/newsmcp/newsmcp-server) — the same data as an MCP server for AI agents.

### Support

Found a problem? Open an issue on the Issues tab and we'll take a look.

# Actor input Schema

## `q` (type: `string`):

Optional search terms matched against headline, one-liner, abstract, and named actors. Space-separated words are ANDed; quote multi-word phrases. Supports AND/OR/NOT, parentheses, and \* wildcards. Leave empty for a filter-only digest.

## `subject` (type: `string`):

A single company, person, place, or organisation to centre the search on (plain name, no quoting needed). Also widens the default time window from 24 hours to 30 days.

## `event_type` (type: `string`):

Exact family.leaf value, e.g. "deals.merger\_acquisition". Comma-separate several values for OR, e.g. "deals.merger\_acquisition,funding.venture\_funding\_round". See the README for the full taxonomy.

## `content_type` (type: `string`):

Form of the reporting. One or more (comma-separated) of: news\_report, press\_release, service\_info, human\_interest, explainer, commentary, analysis, opinion, interview, obituary.

## `sector` (type: `string`):

Industry filter, comma-separated for OR, e.g. "software\_it\_services,semiconductors". See the README for accepted values.

## `min_newsrooms` (type: `integer`):

Minimum number of outlets that reported INDEPENDENTLY (mirrors excluded). 3 means "well-corroborated only".

## `from_date` (type: `string`):

Inclusive lower bound on when the story began (ISO 8601 like "2026-07-01T00:00:00", or relative like "now-6h", "2 days ago"). Defaults to 24 hours ago. Widen this first when a query returns nothing.

## `sort` (type: `string`):

Leave empty for the default (relevance when a query or subject is set, newsrooms otherwise). "trending" = corroboration weighted by freshness.

## `limit` (type: `integer`):

Stories to return (1-50).

## `verbosity` (type: `string`):

How many source links each story carries: compact = none, standard = up to 3, full = every link.

## Actor input object example

```json
{
  "limit": 20,
  "verbosity": "standard"
}
```

# Actor output Schema

## `stories` (type: `string`):

No description

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {};

// Run the Actor and wait for it to finish
const run = await client.actor("newsmcp/news").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {}

# Run the Actor and wait for it to finish
run = client.actor("newsmcp/news").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{}' |
apify call newsmcp/news --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,newsmcp/news"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/7l4csHaZCvvwdzItJ/builds/eqAaeiKY7IgvKbSrC/openapi.json