`get_article_extract`

Pack: wikipedia · Endpoint: https://gateway.pipeworx.io/wikipedia/mcp

Full text of a Wikipedia article by title — the ACTUAL prose AND its tables, not just the lead paragraph. This is how you read a competition schedule, fixture list, medal table, results grid or roster: get_article_extract({title: “Table tennis at the 2026 Asian Games”}) returns the venue, the dates and the day-by-day event schedule. Answers “when is at ”, “what are the dates”, “who won ”, “explain X in detail”, “what does the article say about ”, reading the history/methods/etc. CALL IT DIRECTLY when the title is predictable from the question — Wikipedia titles are regular, so “when is table tennis at the Asian Games” is the article “Table tennis at the 2026 Asian Games”, and the same pattern gives “Athletics at the 2028 Summer Olympics”, “India at the 2026 Asian Games”, “2026 FIFA World Cup”. Constructing the title and reading the article beats searching first, because the search snippet is one truncated line and this returns the whole thing. Titles are exact: on a miss you get a user_error naming search_wikipedia as the recovery. PREFER OVER get_article_summary whenever the lead paragraph is not enough. Omit section for the whole article (capped by max_chars); pass a section number (from get_article_sections) for just that one. Returns plain text with headings marked == like this == and table rows one per line, cells separated by | .

Parameters

Name	Type	Required	Description
`title`	string	yes	Wikipedia article title (e.g. “CRISPR”, “Albert Einstein”).
`section`	number	no	OPTIONAL section number (from get_article_sections) to return just that section. Omit for the full article.
`max_chars`	number	no	Cap on characters returned (1000-100000, default 40000).

Example call

Arguments

{
  "title": "CRISPR"
}

curl

curl -X POST https://gateway.pipeworx.io/wikipedia/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"get_article_extract","arguments":{"title":"CRISPR"}}}'

TypeScript (@pipeworx/sdk)

import { Pipeworx } from '@pipeworx/sdk';
const pipeworx = new Pipeworx();

const result = await pipeworx.call('get_article_extract', {
  "title": "CRISPR"
});

More examples

{
  "title": "Albert Einstein",
  "section": 2,
  "max_chars": 50000
}

{
  "title": "Table tennis at the 2026 Asian Games",
  "section": 1
}

Connect

Add this to your MCP client config, or use one-click install buttons:

{
  "mcpServers": {
    "wikipedia": {
      "url": "https://gateway.pipeworx.io/wikipedia/mcp"
    }
  }
}

See Getting Started for client-specific install steps.

get_article_extract