Skip to main content
Glama
NewsCatcher MCP

NewsCatcher MCP

Official

Search news

search_news
Read-onlyIdempotent

Search recent news from the last 30 days in any language, returning ranked, story-grouped articles with summaries, sources, dates, and links to track companies, people, topics, or events.

Instructions

Search recent news (last 30 days, every language) and get the best articles, ranked and grouped into stories, each with a one-line summary, source, date and link. Use it for anything news-shaped: what happened, latest developments, coverage of a company, person, topic or event, or checking if something was reported. It keeps to real news sources, groups articles into stories (with a newsroom count), translates titles and summaries, and takes exact time windows. For an exact count or every matching article use list_articles; for older news (up to 12 months) use list_articles; to build a dataset or watch companies use start_research.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "search_news"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNorelevance (default) or newest first.relevance
groupNodiverse (default): best articles with repeats of one story discounted; story: one article per story (widest coverage of distinct events); all: every matching article.diverse
limitNoArticles to return (default 10; the free plan allows up to 50).
queryYesWhat to find: a plain-language question or keywords, any language (e.g. "Nvidia earnings guidance", "who is acquiring European banks?"). Upper-case NOT drops a term: "Apple NOT iPhone".
effortNoRanking effort and price: low (1 credit, ~4 s), medium (default, 5 credits, ~8 s, reranked), high (10 credits, ~25 s, LLM-judged, merges duplicate stories).medium
formatNotext (default, compact) or json (machine-readable).text
windowNoHow far back from now: e.g. "2h", "1d", "7d" (default), up to "30d" (longer windows are cut to 30 days; use list_articles for older news).
sourcesNoOnly these publishers: domains, e.g. ["reuters.com","ft.com"].
countriesNoOnly publishers from these countries: ISO 3166-1 alpha-2 codes, e.g. ["US","GB"].
languagesNoOnly these languages: ISO 639-1 codes, e.g. ["en","de"].
min_newsroomsNoOnly stories covered by at least this many newsrooms (a proxy for importance).
exclude_sourcesNoLeave out these publishers (domains).
include_non_newsNoAlso return non-news content (press releases, blogs, opinion). Default false: real news only.
exclude_countriesNoLeave out publishers from these countries (ISO 3166-1 alpha-2).
exclude_languagesNoLeave out these languages (ISO 639-1).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint and idempotentHint, so safety is covered. The description adds real behavioral context beyond that: the 30-day recency ceiling, restriction to genuine news sources, story grouping with a newsroom count, and translation of titles and summaries. It stops short of discussing auth, rate limits or failure modes, which keeps it off a 5.

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

Conciseness4/5

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

Front-loaded with the core action and result shape, then use cases, then alternatives. The final sentence is a dense run-on stacking three alternatives, but each clause still carries routing information rather than 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 15-parameter tool with no output schema, the description supplies the return structure (grouped stories with summary, source, date, link) and the 30-day horizon, which are the details an agent most needs. Minor gaps remain around result volume and credit consumption, though pricing is already enumerated in the effort parameter.

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 every parameter carries a detailed enum or format note, so the schema already does the heavy lifting. The description only reinforces the time-window behavior ('takes exact time windows') and the newsroom-count concept, adding little syntax or format meaning beyond the schema, which is the expected baseline of 3.

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 ('Search recent news') plus the shape of the result: ranked articles grouped into stories with summary, source, date and link. It explicitly contrasts itself with list_articles and start_research, so an agent can distinguish it from siblings without opening a schema.

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

Usage Guidelines5/5

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

Gives concrete when-to-use cases ('what happened, latest developments, coverage of a company, person, topic or event, or checking if something was reported') and names two alternatives with the exact conditions that select them: list_articles for exact counts or older news up to 12 months, start_research for datasets or company watching.

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