Wikipedia MCP server
Last verified: 2026-09
Look up Wikipedia pages without scraping.
Community Browser & search No API key Claude Desktop, Cursor, Windsurf, Claude Code
What it does
Read Wikipedia without a browser. Search, fetch an article, summary, sections, links, coordinates. Each tool also has a wikipedia_ alias.
It sits in Browser & search: Three different jobs get mixed up here.
Good for
- Get an article, summary, or one section without scraping HTML.
- Follow links or related topics from a page.
- Look up coordinates on a place article.
- Ask for a short extract aimed at a specific query.
Tools
- search_wikipedia — Search titles.
- get_article / get_summary / get_sections — Read a page or a slice of it.
- get_links / get_related_topics / get_coordinates — Graph and geo around a page.
- summarize_article_for_query / summarize_article_section — Shorter extracts.
Config (Claude Desktop / Cursor / Windsurf)
Paste the JSON below. Same mcpServers shape. Replace placeholder paths and secrets.
Windows paths look like C:\\Users\\you\\project, not /path/to.
Host-side steps →
Claude Desktop
| OS | Config file |
|---|---|
| macOS | ~/Library/Application Support/Claude/claude_desktop_config.json |
| Windows | %APPDATA%\Claude\claude_desktop_config.json
(usually C:\Users\<you>\AppData\Roaming\Claude\) |
| Linux | ~/.config/Claude/claude_desktop_config.json |
Cursor
| Scope | macOS / Linux | Windows |
|---|---|---|
| This project | .cursor/mcp.json in the repo root | |
| This user | ~/.cursor/mcp.json |
%USERPROFILE%\.cursor\mcp.json |
Windsurf
| OS | Config file |
|---|---|
| macOS / Linux | ~/.codeium/windsurf/mcp_config.json |
| Windows | %USERPROFILE%\.codeium\windsurf\mcp_config.json |
{
"mcpServers": {
"wikipedia": {
"command": "npx",
"args": [
"-y",
"wikipedia-mcp"
]
}
}
}Windsurf remote MCP: use serverUrl instead of url if the block below is HTTP.
One-liner: npx -y wikipedia-mcp
Secrets it wants: none
How to get started
- No key. pipx/uvx wikipedia-mcp or the npm wrapper in the JSON.
- Ask for a page you know exists, then a section.
- Do not treat it as news — Wikipedia lags and can be wrong.
Access risk
Read-only. The failure mode is confident wrong citations, not account takeover.
When to skip it
Skip it when you need the live web (Fetch / Exa) or papers (arXiv).
Instead: Fetch, arXiv, Brave Search.
Vs alternatives
| Server | Official? | Needs a secret? | Best for |
|---|---|---|---|
| Wikipedia | No | No | Look up Wikipedia pages without scraping. |
| Fetch | Yes | Yes | Fetch a URL and turn the page into readable text. |
| arXiv | No | No | Search and read arXiv papers. |
| Brave Search | Yes | Yes | Web search via the Brave Search API. |
More in Browser & search
FAQ
Do I need a key?
No. It hits Wikipedia's API.
Is Wikipedia enough instead of Brave?
For encyclopedia facts, yes. For news or product docs, no — Wikipedia lags and is not a changelog.
Why the wikipedia_ aliases?
The same tools are also exposed with a wikipedia_ prefix so hosts can tell them apart from other search tools.
Can it edit Wikipedia?
No. Read-only.