Skip to content
Wikipedia

WikipediaMCP Server

by cyanheads
Added to Onei
v0.1.13
Apache-2.0
Repository Docs npm
Web & Search

Summary

Search and read Wikipedia from an AI client — summaries, full articles, specific sections, and nearby pages.

Features

  • Search articles and read summaries or full text
  • Target specific sections of long articles
  • Find pages near a geographic location

Installation

Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.

Any MCP-compatible agent

Most agents (Claude, Cursor, Windsurf, VS Code, and more) read a standard mcpServers configuration.

  1. Open your agent's MCP configuration file.
  2. Merge the snippet below into it.
  3. Restart the agent — the "Wikipedia" tools will be available.
{
  "mcpServers": {
    "wikipedia": {
      "command": "npx",
      "args": [
        "-y",
        "@cyanheads/wikipedia-mcp-server"
      ]
    }
  }
}

Description

This MCP server gives an assistant structured access to Wikipedia, which remains one of the better sources for factual grounding on established topics.

What it offers
  • Search across article titles and content
  • Summaries — the lead section, which is usually the right level of detail
  • Full article text when more depth is needed
  • Section targeting, so a long article can be read partially rather than entirely, which matters for context budget
  • Geographic search for pages near a set of coordinates
  • Language selection across Wikipedia's editions
  • Related pages and links for exploring a topic
Why bother when the model already knows

Two reasons. Currency — Wikipedia is updated continuously and training data is not. And verifiability — an answer with a Wikipedia citation can be checked, while an answer from parametric memory cannot.

It is also the cheapest way to reduce confident errors on the long tail of factual questions, where a model's recollection is thinnest.

Setup

No API key or account required. Runs with npx -y @cyanheads/wikipedia-mcp-server. Please respect Wikimedia's rate limits.

Related MCP Servers

MCP: Engram

by Gentleman Programming

Featured

Persistent memory for coding agents as a single Go binary — SQLite and FTS5 behind MCP, an HTTP API, a CLI and a TUI, with no Node, Python or Docker required.

Developer Tools

MCP: OKF Agent Memory

by okf-memory

Git-native persistent memory for coding agents — sub-300µs BM25 search over version-controlled plain text, with no embeddings, no database and no API costs.

Databases & Data
Browse all MCP servers →