About Wikimedia Rest
Wikimedia Rest is an MCP server for accessing Wikimedia REST API content without authentication. It serves developers and research workflows with page details, media, references, and date-based features across Wikimedia projects.
Key features
- 01Page summaries and HTML
- 02Metadata and references
- 03Images and videos
- 04Related pages and revisions
- 05Featured and on-this-day content
- 06Random page summaries
Use cases
- 01Retrieve a page overview for research
- 02Inspect references and media on a page
- 03Check recent page revisions
- 04Find daily featured or historical content
MCP support
Exposes Wikimedia REST API operations as tools for MCP clients, including page, media, and date-based queries. It can run locally over stdio or through the Pipeworx gateway.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://gateway.pipeworx.io/wikimedia-rest/mcpclaude mcp add --transport http pipeworx-io-wikimedia-rest https://gateway.pipeworx.io/wikimedia-rest/mcp{"mcpServers":{"pipeworx-io-wikimedia-rest":{"type":"http","url":"https://gateway.pipeworx.io/wikimedia-rest/mcp"}}}Open in Cursor{"servers":{"pipeworx-io-wikimedia-rest":{"type":"http","url":"https://gateway.pipeworx.io/wikimedia-rest/mcp"}}}Open in VS Code{"mcpServers":{"pipeworx-io-wikimedia-rest":{"type":"http","url":"https://gateway.pipeworx.io/wikimedia-rest/mcp"}}}{"mcpServers":{"pipeworx-io-wikimedia-rest":{"serverUrl":"https://gateway.pipeworx.io/wikimedia-rest/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project README@pipeworx/wikimedia-rest
Wikimedia REST API v1 MCP — keyless access to Wikipedia/Wikimedia content endpoints (different surface from the wikipedia action API).
Part of Pipeworx — an MCP gateway connecting AI agents to 1684+ live data sources.
Tools
page_summary(title, project?, lang?)— page summary card (description, extract, thumbnail) — same shape as the "did you mean" cardpage_html(title, project?, lang?)— page HTML (Parsoid output)page_metadata(title, project?, lang?)— page metadatapage_references(title, project?, lang?)— references on a pagepage_media(title, project?, lang?)— images + videos on a pagepage_related(title, project?, lang?)— related pagespage_revisions(title, project?, lang?)— recent revisionspage_pdf(title, project?, lang?)— returns URL only (the PDF endpoint streams binary)featured(year, month, day, project?, lang?)— daily featured content (TFA, MP image, news, on-this-day, most-read)onthisday(type, month, day, project?, lang?)— on-this-day events (all|births|deaths|events|holidays|selected)random(project?, lang?)— random page summary
project defaults to wikipedia, lang to en. Other projects: wikinews, wikiquote, wiktionary, wikivoyage, wikibooks, wikiversity, wikisource.
Data source
https://<lang>.<project>.org/api/rest_v1
Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"wikimedia-rest": {
"url": "https://gateway.pipeworx.io/wikimedia-rest/mcp"
}
}
}
What this endpoint actually serves
tools/list at https://gateway.pipeworx.io/wikimedia-rest/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1684+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
No MCP client? Call it over HTTP
curl -X POST https://gateway.pipeworx.io/v1/tools/page_summary \
-H 'Content-Type: application/json' \
-d '{"title":"Albert Einstein"}'
No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/page_summary. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.
Standalone (no gateway account)
This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:
{
"mcpServers": {
"wikimedia-rest": {
"command": "npx",
"args": ["-y", "@pipeworx/mcp-wikimedia-rest"]
}
}
}
Or run it directly to confirm it starts:
npx -y @pipeworx/mcp-wikimedia-rest
It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call
for only this pack's tools — none of the shared meta-tools the gateway
connection above adds. Same source, same tools, no ask_pipeworx routing.
Using with ask_pipeworx
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Wikimedia Rest data" })
The gateway picks the right tool and fills the arguments automatically.
More
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.