mcpField
M
mcp-news-media-mention-monitor

mcp-news-media-mention-monitor

Local
github.com/mambalabsdevSearch0Updated 1w ago

About mcp-news-media-mention-monitor

An MCP server that tracks Google News articles about companies, brands, people, or topics. It returns publisher URLs and headline sentiment labels, and can use a state key to return only newly found articles on repeat calls.

Key features

  1. 01Search Google News for queries
  2. 02Return publisher URLs and domains
  3. 03Label headline sentiment
  4. 04Deduplicate articles across search terms
  5. 05Track only new results with a state key

Use cases

  1. 01Monitor news coverage of a company
  2. 02Review recent headlines about a brand or person
  3. 03Check for new articles between recurring searches

MCP support

Exposes the monitor_news_mentions tool to MCP clients. It runs the Apify actor and returns article rows, with state-based filtering for new results.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"com-mambabuilt-mcp-news-media-mention-monitor": {
"command": "npx",
"args": [
"-y",
"@mambalabsdev/mcp-news-media-mention-monitor"
],
"env": {
"APIFY_TOKEN": "<APIFY_TOKEN>"
}
}
}
}
Run commandnpx -y @mambalabsdev/mcp-news-media-mention-monitor
Environment variables to set
APIFY_TOKENSecretApify API token from https://console.apify.com/account/integrations

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@mambalabsdev/mcp-news-media-mention-monitor1.0.1

Tools

1

Saved tool list · updated 1w ago

ParameterTypeRequiredDescription
countryenumNoGoogle News country edition. Default US.US | GB | CA | AU | IE | NZ | IN | SG | ZA | DE | AT | CH | FR | BE | NL | ES | MX | AR | BR | PT | IT | SE | NO | DK | FI | PL | JP | KR | IL | AE
queriesarrayYes1 to 50 search terms: company names, brands, people, or topics. Put a phrase in double quotes for an exact match.
languagestringNoLanguage code of the edition, for example en, de, or pt-419. Default en.
only_newenumNotrue (default): skip articles an earlier run with the same state_key returned.true | false
state_keystringNoName for this watch list, for example acme-weekly.
since_daysstringNoDays back, 1 to 90. Default 7.
max_articlesstringNoMost articles per search term, 1 to 100, newest first. Default 50.
exclude_termsarrayNoUp to 20 words to leave out of every search.
max_charge_usdstringNoOptional cap on this run's cost in USD.
resolve_publisher_urlenumNotrue (default): resolve each article to the publisher's own URL.true | false

Details

From the project README

News and Media Mention Monitor MCP Server

npm version license

News and Media Mention Monitor MCP server

An MCP server for the Mamba Labs News and Media Mention Monitor actor on Apify. Give it company names, brands, people, or topics. It reads Google News for each one and returns one row per article: headline, outlet, date, the publisher's own URL and domain, and a headline sentiment label. With only_new on, a repeat call with the same state_key returns only articles it has not returned before.

What's Inside

What it does

Each news.google.com link is resolved to the article's URL on the publisher's site. An article found by two of your search terms comes back once. When a run returns no article, one free summary row says why: nothing matched, everything was returned before, or Google News did not answer. All of the work runs on Apify. This package is a thin client that starts the actor run, waits for it, and hands back the dataset rows.

Quick start

You need Node.js 18 or newer and an Apify account with an API token.

Add this to your Claude Desktop config (claude_desktop_config.json), Cursor, or any MCP client:

{
  "mcpServers": {
    "mamba-news-media-mention-monitor": {
      "command": "npx",
      "args": [
        "-y",
        "@mambalabsdev/mcp-news-media-mention-monitor"
      ],
      "env": {
        "APIFY_TOKEN": "your-apify-token"
      }
    }
  }
}

Restart the client. The monitor_news_mentions tool appears.

Prerequisites

Example prompts

  • "What did the news say about Gong and Salesloft this week?"
  • "Find news articles about our company from the last 30 days and list the outlets."
  • "Any negative headlines about Acme Robotics since my last check?"

Tool

monitor_news_mentions. One tool. Example arguments:

{
  "queries": ["\"Acme Robotics\""],
  "since_days": "7",
  "state_key": "acme-weekly"
}

Inputs

Every buyer facing input of the actor, unchanged. Omitted inputs take the actor's own defaults. Numbers and yes or no values are sent as strings.

InputTypeDescription
queriesarray1 to 50 search terms. Required
exclude_termsarrayUp to 20 words to leave out
since_daysstringDays back, 1 to 90. Default 7
countrystringGoogle News country edition. Default US
languagestringLanguage code. Default en
resolve_publisher_urlstringtrue (default) or false
only_newstringtrue (default) or false
state_keystringName for this watch list
max_articlesstringPer search term, 1 to 100. Default 50
max_charge_usdstringOptional cap on the run's cost

Pricing

Pay per event on Apify, billed to your Apify account. Prices in USD.

EventFree planBronzeSilverGold
article-row, per article returned$0.0023$0.002185$0.00207$0.001955
apify-actor-start, per run start$0.0015$0.0015$0.0015$0.0015

An article skipped by only_new is not charged. A summary row is free.

Your keys

The actor needs no key and holds none. Proxy traffic adds nothing to your price: Mamba Labs pays the platform costs of the run.

Full actor documentation

apify.com/mambalabs/news-media-mention-monitor

License

MIT. See LICENSE.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.