🧩 Wikipedia & Wikidata API: Entity Facts, Summary & Pageviews

One call, Wikipedia + Wikidata, one brief. Give an entity name (company, person, place, thing) and get a single structured brief — summary, resolved facts (type, country, inception, website, HQ, industry, CEO, founder, population, revenue…), coordinates, and a 30-day popularity signal — instead of scraping Wikipedia and crawling Wikidata yourself.

Headless · keyless · structured JSON out · built for AI agents (grounding & enrichment).

⚡ Why it's different

Other actors dump raw Wikipedia text. This one resolves and fuses: it maps the page to its Wikidata entity, pulls the structured claims, resolves their labels, and adds popularity — so you get ceo: Sam Altman, country: United States, inception: 2015-12-11, not a wall of prose.

📋 What you get (per entity)

Field	Meaning
title, wikidataId	Resolved canonical name + Wikidata QID
description, extract	Short description + lead summary
facts	Structured: instanceOf, country, inception, officialWebsite, headquarters, industry, ceo, founder, capital, population, employees, revenueUsd, motto
coordinates	lat/lon (for places/HQs)
url, thumbnail	Wikipedia page + image
monthlyPageviews	Views in the last 30 days (popularity)
isDisambiguation, resolved	Flags for ambiguous/unfound names

📥 Input

Field	Type	Meaning
entity	string	A single name, e.g. OpenAI
entities	array	Many names: ["OpenAI","Spain","Bitcoin"] (billed per entity)
language	string	Wikipedia language edition (default en)
webhookUrl	string	POST the briefs here (Zapier/Make/n8n/custom)

Example input

{ "entities": ["OpenAI", "Spain", "Bitcoin"], "language": "en" }

📤 Output (one row per entity)

{
  "query": "OpenAI", "resolved": true, "title": "OpenAI", "wikidataId": "Q21708200",
  "description": "American artificial intelligence company",
  "extract": "OpenAI is an American artificial intelligence ...",
  "url": "https://en.wikipedia.org/wiki/OpenAI", "thumbnail": "https://.../OpenAI_Logo.svg.png",
  "coordinates": { "lat": 37.76, "lon": -122.41 },
  "facts": {
    "instanceOf": { "qid": "Q6881511", "label": "enterprise" },
    "country": { "qid": "Q30", "label": "United States" },
    "inception": { "value": "2015-12-11" },
    "officialWebsite": { "value": "https://openai.com/" },
    "ceo": { "qid": "Q7407093", "label": "Sam Altman" },
    "industry": { "qid": "Q11660", "label": "artificial intelligence" },
    "employees": { "value": 4500 }
  },
  "hasFacts": true, "monthlyPageviews": 354585,
  "sources": ["wikipedia.org", "wikidata.org", "wikimedia.org (pageviews)"],
  "capturedAt": "2026-..."
}

💰 Pricing (pay-per-event menu)

• entity-resolved — base, per entity returned.
• facts-enriched — premium, per entity that yields structured Wikidata facts (the high-value outcome).

💡 Use cases

• Agent grounding / disambiguation: resolve "Apple" → the company, with QID + facts, in one call.
• Enrichment: turn a list of company/person names into structured records.
• RAG / knowledge: fetch a vetted summary + facts + source URL to ground an answer.
• Research dashboards: popularity (pageviews) + key facts across many entities.

🤖 For AI agents (MCP)

Keyless, one call → a resolved, fused, structured brief with the Wikidata QID for further hops. Example MCP server config:

{
  "mcpServers": {
    "entity-brief": {
      "url": "https://mcp.apify.com/?tools=actors,docs,centorprat/wikipedia-wikidata-api"
    }
  }
}

Claude Code: claude mcp add --transport http apify "https://mcp.apify.com/?tools=actors,docs,centorprat/wikipedia-wikidata-api" --header "Authorization: Bearer <YOUR_APIFY_TOKEN>"

No extra setup: this Actor is callable from Claude, Cursor, ChatGPT or any MCP client through the Apify MCP server, and agents can find it on their own with the server's search-actors tool.

🚀 Ready-made tasks (one click)

Pre-configured runs for the most common jobs. Open one, change the input, run:

• Company Facts from Wikipedia & Wikidata: Structured company facts from Wikipedia and Wikidata: CEO, HQ, founding date, industry, website and pageviews for any list of companies.
• Wikipedia Summary for Any Topic: Clean Wikipedia summaries for any list of topics with Wikidata ID, description, image and key facts. Any language. LLM-ready JSON.
• Wikipedia Pageviews: How Popular Is It?: Compare popularity of people, brands and topics with 30-day Wikipedia pageviews, plus summary and Wikidata facts. Bulk, keyless.

❓ FAQ

• Do I need an API key? No — Wikipedia and Wikidata are keyless with generous limits.
• What counts as an entity? Anything with a Wikipedia page: companies, people, places, products, concepts.
• Ambiguous names? If the page is a disambiguation, isDisambiguation is true — refine the name.
• Not found? resolved is false and the row carries just your query (so nothing is lost).
• Which facts? A curated set of high-value Wikidata properties; item values are label-resolved.
• Other languages? Yes — set language (e.g. es, de); facts/labels resolve in that language.
• How fresh is popularity? monthlyPageviews sums the last ~30 days of Wikipedia views.
• Is data stored? No — fetched, composed, returned.
• Commercial use? Wikipedia & Wikidata are free content (CC BY-SA / CC0); attribute as appropriate.

📜 Data & attribution

Summaries from Wikipedia (CC BY-SA), structured facts from Wikidata (CC0), popularity from the Wikimedia pageviews API. Public data, composed and returned; nothing stored.

🔗 Related actors

Part of one suite of keyless, agent-ready composers by the same developer:

• Shopify Store Leads + App Audit (Reviews, Email, Pixels): Shopify stores by niche, verified and audited for missing apps (reviews, email/SMS, upsell, loyalty, chat, subscriptions), pixels and theme: scored leads with emails.
• Google Maps Leads + Website Audit for Agencies: local businesses from Google Maps audited for website, Google profile, reviews, booking and tracking gaps: scored, explained leads with phone and emails.
• FEMA Flood Zone & Property Risk API - Zillow/Redfin Enricher: FEMA flood zone + 18-hazard FEMA risk index + neighborhood demographics per US address, or for a whole Zillow/Redfin dataset.
• Domain Lookup API - DNS, MX, SPF, Tech & Contact Emails: DNS + live homepage → IPs, MX/SPF, tech, socials and public contacts per domain.
• Country Economic Data API - World Bank GDP, FX & Holidays: World Bank + FX + public holidays → one market brief per country.
• Weather, Air Quality & Earthquake Risk API by Location: live weather + air quality + earthquakes → one clear/caution/hazard verdict per point, worldwide.
• Aircraft Tracker API (ADS-B) - Approach & Military Alerts: aircraft approaching a point with CPA/ETA + military/unidentified flags and alerts.
• NARA Catalog Extractor: US National Archives catalog search → digital-object download URLs + metadata.