Skip to main content
Glama
subimpact

subimpact-data-mcp

Official
by subimpact
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

news_mentions

Search publisher news feeds by keyword to monitor brand mentions, track competitors, and collect article titles, snippets, URLs, and publish dates across Malaysia, Southeast Asia, and global outlets.

Instructions

News Mentions API: Brand & Keyword Monitoring

Search a curated index of publisher news feeds by keyword and get clean article rows: title, snippet, publisher URL, source, region, topic, language and publish time. Built for brand/PR monitoring, competitor tracking and market news in Malaysia, Southeast Asia and worldwide. Pay only per article.

Pricing (pay per event, billed to your Apify account): Article: $0.001; platform usage billed to your account.

Runs on Apify as subimpact/news-mentions-api.

Input Schema

NameRequiredDescriptionDefault
dateToNoOnly articles published on/before this date (inclusive; a bare date covers the whole day). ISO format: 2026-10-24 or 2026-10-24T18:00:00Z.
topicsNoPublisher sections to search. Leave empty for all topics.
domainsNoRestrict results to these publisher domains (subdomains included): thestar.com.my also matches biz.thestar.com.my. Leave empty for any publisher.
onlyNewNoFor scheduled monitoring: remembers how far the index it has been read (in the named key-value store news-mentions-state) and returns only articles added since. The first run returns the lookback window. Do not mix delta and full runs in the same task.
regionsNoPublisher regions to search. Leave empty for all regions. MY = Malaysia, SG = Singapore, ID = Indonesia, PH = Philippines, TH = Thailand, VN = Vietnam, GLOBAL = international outlets.
dateFromNoOnly articles published on/after this date. ISO format: 2026-10-01 or 2026-10-01T09:00:00Z.
keywordsYes1–100 search queries. Defaults to a demo query when omitted. Query syntax: words are ANDed by default (petronas profit = both words); "exact phrase" in double quotes; OR between terms (uppercase); -term or -"phrase" excludes. Example: Petronas OR "Petronas Dagangan" -sponsored.
stateKeyNoOnly for onlyNew. Name of the stored cursor. Leave empty to derive it from the query (keywords + filters), so different searches keep separate cursors in the same task.
_maxItemsNoHow many dataset items to return to the model (1-1000, default 50). Truncates the response only; it does not change what the Actor collects or charges for.
languagesNoISO language codes of the publisher feed, e.g. en, ms, id, th, vi. Leave empty for all languages.
lookbackDaysNoHow many days back to search, counted from now (1–180). The index keeps up to 180 days of history. Ignored when dateFrom is set, and on scheduled delta runs (onlyNew) after the first run.
_maxChargeUsdNoPer-run spending cap in USD (default 0.5). Passed to Apify as the run option maxTotalChargeUsd, so the run stops when it reaches this charge.
excludeDomainsNoDrop results from these publisher domains (subdomains included).
excludeKeywordsNoAppended to every query as -term, so you can filter noise once instead of in each keyword. Multi-word terms are quoted automatically: "press release" becomes -"press release".
maxItemsPerKeywordNoUpper limit of articles fetched for each keyword (1–5000). You are charged only for the articles actually returned.
dedupeAcrossKeywordsNoOn (default): an article matching several keywords appears once, with every matching keyword in matchedKeywords. Off: one row per keyword match, pushed as soon as it is fetched.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does a decent job: it discloses the paid, per-article billing model (Article: $0.001 plus platform usage) and describes the response shape (title, snippet, publisher URL, source, region, topic, language, publish time). It does not cover authentication/setup (Apify account/token) or whether results come back synchronously versus requiring a run/poll workflow, which is a notable gap for an actor-based tool.

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?

The description is front-loaded with purpose and return shape, then cost, then platform. The pricing sentence is slightly marketing-flavored but is legitimately useful cost transparency. Four short paragraphs with little waste.

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 16-parameter, no-annotation, no-output-schema tool, the description covers purpose, output fields, and cost model, which is most of what an agent needs. What is missing is operational context—whether the call returns dataset rows directly or triggers an Apify run that must be retrieved via get_run_results—which matters given that sibling tool exists.

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 description coverage is 100%, so every one of the 16 parameters is already documented in detail (query syntax, delta mode, state keys, lookback, spending cap). The description adds only a high-level mention of keyword searching and returned fields, so per the coverage rule the baseline of 3 applies.

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

Purpose4/5

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

The description names a specific verb (search) and resource (a curated index of publisher news feeds), and enumerates the returned fields and target use cases (brand/PR monitoring, competitor tracking). That is far more than a restatement of the name. It stops short of explicitly distinguishing itself from general-search siblings like google_search or google_ai_mode, leaving the agent to infer that this tool is news-index-specific.

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?

It gives clear usage context: 'Built for brand/PR monitoring, competitor tracking and market news in Malaysia, Southeast Asia and worldwide,' which signals when the tool is a fit. It does not name alternatives or state exclusions (e.g., when to prefer google_search over this index), so it is a solid 4 rather than a 5.

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

Deploy Server

Other Tools