SkimNews
Server Details
Free AI-curated news summaries from 100+ sources across seven beats, plus entity dossiers.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 4 tools
Each tool targets a distinct retrieval mode: today's stories (get_top_stories), archive search (search_stories), single-story detail (get_story_detail), and entity dossiers (get_entity_file). There is mild potential confusion between search_stories and get_entity_file when asking 'what's the latest on X', but the descriptions explicitly separate trackable entities from topic/theme searches.
All names use snake_case and mostly follow a get_<noun> pattern, which is readable. The one deviation is search_stories using a different verb, plus minor noun-order variance (entity_file vs story_detail), but the set remains predictable.
Four tools is slightly lean for a news platform but each covers a meaningful workflow (discovery, search, detail, entity tracking). No redundant tools, though a beat/category lister might justify one more.
The surface covers the core read lifecycle: find today's stories, search the archive, drill into a story, and track entities. Minor gaps exist (no beat/category enumeration, no explicit date-range or pagination controls), but agents can work around these via the existing tools.
Available Tools
4 toolsget_entity_fileGet an entity dossierARead-onlyIdempotentInspect
SkimNews keeps a permanent dossier on every person, organisation, product, law, or place it has covered repeatedly. Returns the current 3-sentence status, 60-day mention/source counts, recent coverage, and related entities. Use for "what has SkimNews covered about X" and "what's the latest on X" where X is a trackable entity. Slug form, e.g. 'trump', 'openai', 'iran'.
Inputs: slug. Returns: url, name, slug, type, +8 more
get_story_detailGet a story's full detailARead-onlyIdempotentInspect
The full SkimNews treatment of one story: summary, why-it-matters, sourced bullet points, editorial take, named entities, the source taxonomy, and the canonical URL. Accepts an article id (e.g. '46b45d01'), a canonical skimnews.com URL, or an article slug. Use after get_top_stories or search_stories when a story needs detail or accurate citation.
Inputs: identifier (required). Returns: id, url, image, match, +13 more
get_top_storiesGet today's top storiesARead-onlyIdempotentInspect
Today's top SkimNews stories, optionally limited to one beat. Use this for "what's happening today" / "today's news" / "latest in " questions. Returns summaries plus canonical URLs per story. Categories: geopolitics, tech, finance, health, energy, sports, culture.
Inputs: limit, category. Returns: count, stories, generated_at, categories_included
search_storiesSearch SkimNews storiesARead-onlyIdempotentInspect
Semantically search SkimNews' archive of 47,000+ summarised stories by topic, theme, or news event, ranked by relevance. Use this to find coverage of a subject across SkimNews' history rather than only today. Returns summaries plus canonical URLs. An empty result list means SkimNews has not covered that topic — say so rather than substituting unrelated stories.
Inputs: query (required), days, limit, category. Returns: days, mode, count, query, +1 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Curated news search and deep research reports for your reader: tech, AI, business, policy, media.
Free AI news, ranked stories by section, and trending topics. No authentication required.
Private company data, entity-resolved news, targeted lists, and alternative signals for AI agents.
Daily and weekly AI briefings on the stocks you hold, plus per-ticker news with sources.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceReal-time curated knowledge API for AI agents. Updated Mon/Wed/Fri from 31 sources covering AI/tech, startups, alternative markets, and emerging markets — no scraping or storage required.1MIT
- AlicenseAqualityBmaintenanceReal-time financial news for AI agents and trading bots — AI-enriched stories with per-ticker analysis, a 1–10 relevance score, SEC Form-4 insider transactions, plus trending and "actionable-now" feeds. Free tier, OAuth, no API key to paste.2113MIT

ultralayer-v0official
AlicenseNot gradedqualityBmaintenanceRealtime financial context for AI agents: what changed, who is affected, and what to watch next. One suite covering news, events, guidance, filing changes, sentiment, stakeholders, and alerts. Information-efficient responses with evidence for every result. First-class point-in-time safety for backtests. Pairs well with web search and a market-data API. All data is our own.3MIT- FlicenseNot gradedqualityCmaintenanceEnables AI agents to search and read every original Breaking News story and long-form Desk piece, returning full text, sources, URLs, and citation lines through free, read-only tools.-
Glama MCP Gateway
Add one secure layer between your agents and this server.