MCP server exposing 11 tools for wikimedia-rest.
This URL is a JSON-RPC 2.0 endpoint over HTTP. Issue POST requests with a JSON-RPC body. Browsers and search crawlers land here on GET.
POST https://gateway.pipeworx.io/wikimedia-rest/mcp
Content-Type: application/json
{"jsonrpc":"2.0","id":1,"method":"tools/list"}page_summary — "What is X" / "who is X" / "tell me about X" / "Wikipedia summary of X" / "biography of X" / "history of X" — fetches the Wikipedia article extract (title, description, thumbnail, lead-paragraph extract) for any topic, person, place, event, or concept. Use whenever an agent needs a quick encyclopedic reference. Defaults to en.wikipedia.org; pass project/lang for other Wikimedia projects or languages. Example: page_summary({ title: "Albert Einstein" }).page_html — Full Wikipedia article HTML (Parsoid output) — use when page_summary's extract isn't enough and you need the complete article body, infoboxes, tables, and embedded content. Returns rendered HTML you can scrape/parse for full-text questions.page_metadata — Wikipedia article metadata: categories, inter-language links, content_urls (desktop/mobile), page_id, and namespace (ns). Use to get canonical IDs, discover language versions, or check which categories an article belongs to.page_references — Citations / references / sources cited by a Wikipedia article. Use for "what sources back the claim that…", "where does Wikipedia cite this from", or to harvest authoritative external links on a topic.page_media — Images, videos, and other media embedded in a Wikipedia article. Use for "show me pictures of X", "what images are on the X Wikipedia page", or to find Commons-hosted media tied to a topic.page_related — "What's related to X" / "see also" — Wikipedia's related-articles graph for any topic. Returns up to ~12 related pages with summaries. Use for "what should I read next", topic exploration, or finding adjacent concepts.page_revisions — Recent edit history for a Wikipedia article — editor usernames, timestamps, revision sizes, and edit comments. Use to check when an article was last updated, spot recent disputes, or assess reliability before quoting.page_pdf — Returns a Mapbox static-tile image URL for a Wikipedia article as a PDF download. Caller fetches the binary PDF directly from the returned URL via browser or curl. Pass title plus optional project/lang for non-English Wikimedia projects.featured — Wikipedia's "today's featured" content for a specific date — featured article, most-read, picture of the day, on-this-day events. Use for "what's on Wikipedia today", "featured article on 2026-05-21", or to seed daily-roundup content.onthisday — "What happened on this day" / "events that happened on May 21" / "historical events on a date" — births, deaths, events, holidays, and selected occurrences from history for any month+day. Pass type="all" for everything, or filter to "births" / "deaths" / "events" / "holidays" / "selected".random — Random Wikipedia article summary — pick a random article from the encyclopedia. Use for "give me a random Wikipedia article", "surprise me", or seeding exploration. Returns the same shape as page_summary.Code samples (curl / TypeScript / one-click client install), schemas, and the live playground are on the pack page:
https://pipeworx.io/packs/wikimedia-rest/
Pipeworx is an open MCP gateway connecting AI agents to live data. pipeworx.io