search_wikipediaLABSCO SUMMARY
Wikipedia at the granularity you ask for.
The difference from a generic page fetch is that you choose the size of what comes back — a query-shaped summary, one section, a plain-text extract or the raw wikitext — so a long article does not have to arrive whole. Parallel search runs several queries at once, which turns a comparison question into one round trip instead of five.
What it is
A TypeScript server deployed on Vercel that puts Wikipedia behind MCP: ranked search, full articles or raw wikitext, query-specific summaries, section extraction and internal links, across 50+ languages.
What you get
- Article search with relevance ranking
- Several queries run in parallel in one call
- A full article as a plain-text extract or as complete wikitext
- A summary written against the specific question you asked, not the generic lede
- Individual sections extracted and summarised
- Internal links and related articles from an article
- 50+ language codes and matching country codes, resolved automatically
- Input sanitisation and tiered rate limiting on the server side
Requirements
There is no public instance to point at: deploy your own copy — clone the repo and run vercel — then connect clients to your deployment's /mcp URL. It speaks MCP Streamable HTTP and runs stateless, which suits serverless. Language and country default to en and US, and both can be set in the environment.
Setup effort
One command — claude mcp add wikipedia --transport http https://<YOUR_APP>.vercel.app/mcp
USE CASES
01
Getting a fact without reading the whole article
Ask for a summary written against your question rather than the generic opening paragraph.
02
Researching several things at once
Run the queries in parallel in a single call instead of searching one at a time.
03
Pulling one section out of a long article
Extract the section you need and leave the rest behind.
04
Following a topic outward
Read the internal links and related articles to work out what to look at next.
05
Working with the source text
Get the complete wikitext when the plain-text extract loses the structure you need.
06
Reading in another language
Set the language code — 50+ are supported, and country codes resolve to one automatically.
13 tools
Listed in project docs. Your client may show a different list.
multi_search_wikipediaget_articleget_summaryget_sectionsget_linksget_coordinatesget_related_topicssummarize_article_for_querysummarize_article_sectionextract_key_factstest_wikipedia_connectivitylist_supported_countriesBEFORE YOU INSTALL
What to know first
Tools you get
13 tools named in the project's documentation.
Requires
- A client that can reach a remote MCP server over HTTP
- A Vercel account and the vercel CLI, to deploy your own copy
INSTALLATION
Connect your client
Server setup
Setup
TERMINAL
git clone https://github.com/Ravishka17/Wikipedia-MCP
cd Wikipedia-MCP
vercelclaude mcp add
Claude Code
TERMINAL
claude mcp add wikipedia --transport http https://<YOUR_APP>.vercel.app/mcp
