Wikipedia article summary (21 languages) ($0.0018)
wiki_summaryRead-onlyIdempotent
PAID ($0.0018 USDC via x402). Resolve a title or a few words to a Wikipedia article (en, ar, de, fr, es, it, ja, zh, ru, pt, nl, pl, tr, fa, he, ko, id, uk, sv, vi, hi) and return its summary: lead section as plain text (not the whole article), description, URL, last edit, image, coordinates, Wikidata id, how it was matched, other matches. Disambiguation pages are labelled. No fitting title answers 404 and is not charged. Text is CC BY-SA 4.0, attribution included. Without payment this returns the 402 challenge; the fiatdock-mcp npm package pays automatically. Any answer the tool cannot produce is >= 400 and is NOT charged.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | Wikipedia language edition (default en): en, ar, de, fr, es, it, ja, zh, ru, pt, nl, pl, tr, fa, he, ko, id, uk, sv, vi, hi | |
| query | No | An article title or a few words naming the subject (required; an empty body answers the published example) | |
| payment | No | Base64 of a single x402 v2 PaymentPayload (EIP-3009 transferWithAuthorization on Base USDC). OMIT it on the first call: the 402 you get back carries `howToPay.payloadTemplate` — the exact envelope to fill in — plus the price and the EIP-712 domain. Send it on the second call to complete the purchase; it is forwarded as the PAYMENT-SIGNATURE header, never as body data. Nothing is charged for the 402 itself, and a call that fails after payment settles nothing. |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The article's canonical desktop URL | |
| asOf | Yes | ISO time the search and the summary were read (the older of them) | |
| lang | Yes | The Wikipedia language edition read | |
| note | Yes | Whose text it is, how the article was chosen, and the limits | |
| type | Yes | standard, disambiguation (a list of meanings, not an answer), mainpage, no-extract, or unknown | |
| query | Yes | The query as searched (whitespace collapsed) | |
| title | Yes | The article's title | |
| source | Yes | Where the data came from | |
| extract | Yes | The article's lead section as plain text (at most 4,000 characters) — Wikipedia contributors' text | |
| license | Yes | The license of the text (CC BY-SA 4.0) | |
| defaulted | No | Present only when the body was empty: which query the answer is for, and why | |
| matchedBy | Yes | How the article was chosen: exact title, full-text search or title search | |
| thumbnail | Yes | The article's lead image (https), or null | |
| wikidataId | Yes | The Wikidata item (Q-id), or null | |
| attribution | Yes | The credit to keep beside any reuse of the text, with the article's link | |
| coordinates | Yes | The subject's coordinates when the article has them, or null | |
| description | Yes | The short description (usually Wikidata's), or null | |
| lastModified | Yes | ISO time of the article's last edit, or null | |
| matchedTitle | Yes | The redirect or alias title that matched, when it differs from the article's title (e.g. HTTP 402 → List of HTTP status codes) | |
| otherMatches | Yes | Up to 4 other titles the search returned |