Skip to main content
Glama

Google News RSS Scraper

google_news_rss

Scrape Google News RSS by keyword, topic, site or geo, then filter by language, country and date to return headlines, publishers, dates and decoded URLs for news and media monitoring.

Instructions

Scrape Google News via official RSS by keyword, topic, site or geo. Filter by language, country and date (when: 1h, 1d, 7d, 30d). Returns headlines, publishers, published dates and decoded publisher URLs. No login and no proxy. Use this for news monitoring, media monitoring, SEO and research. Van Born Labs. $1.00 per 1,000 articles, billed to your Apify account.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "google_news_rss"
  }
}

Input Schema

NameRequiredDescriptionDefault
geoNoGoogle News geo topic, e.g. California or London. Uses the official geo headlines feed.
whenNoLimit keyword/site searches to recent articles (Google's when: operator). Topic feeds are filtered by published date instead. Options: (empty) = Any time; 1h = Past hour; 1d = Past 24 hours; 7d = Past 7 days; 30d = Past 30 days.
sitesNoPublisher domains (bbc.com, reuters.com). Applied as site:domain in the search query.
dateToNoISO date (YYYY-MM-DD). Added as before: to keyword searches and used as a published-date filter.
topicsNoOfficial Google News topic feeds, in addition to keyword searches.
countryNoISO country code (e.g. US, GB, DE, FR, JP, IN, BR).US
queriesNoGoogle News search queries (e.g. openai, "climate change"). Combined with site filters and date filters when those are set.
dateFromNoISO date (YYYY-MM-DD). Added as after: to keyword searches and used as a published-date filter.
languageNoISO language code for Google News (e.g. en, de, fr, ja, es, pt-BR).en
maxItemsNoHard cap on articles scraped (and charged) in this run. Google News RSS typically returns up to 100 items per feed. Defaults to 5 in this MCP server to keep runs cheap.
decodeUrlsNoResolve news.google.com wrapper links to the real publisher URL (two extra official Google requests per article, no proxy). If decoding fails, the Google News link is kept.
maxConcurrencyNoParallel HTTP requests (feeds and URL decoding).
includeTopStoriesNoAlso fetch the Top stories feed for the selected language and country. Used automatically when no query, topic, site or geo is given.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare it as a non-read-only, open-world, non-destructive, non-idempotent operation, so the description adds real value: no login or proxy required, returned fields, and crucially the cost model ($1.00 per 1,000 articles billed to the Apify account). It does not state failure/partial-result behavior or latency implications beyond concurrency defaults.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences, capability front-loaded first, then filters, then return shape, then constraints and cost. Minor branding text ('Van Born Labs') is the only filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 13-parameter, zero-required, paid scraping tool with no output schema, the description covers inputs, outputs, cost and auth adequately. A little more detail on default behavior (maxItems default of 5 per run and its billing impact) would close the remaining gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the description mirrors what the schema already documents — language/country/date filters and the when: values already enumerated in the `when` parameter. The mention of 'decoded publisher URLs' loosely ties to decodeUrls but adds no new semantics beyond the structured fields, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Scrape Google News via official RSS') plus the four selection dimensions (keyword, topic, site, geo) and what is returned. An agent can distinguish it from the sibling tools (YouTube, ATS, email validator) without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear usage contexts — news monitoring, media monitoring, SEO and research — so an agent knows when the tool applies. It stops short of naming alternatives or explicit when-not conditions, and the schema's includeTopStories note about falling back when no query/topic/site/geo is given is not carried into the description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.