# Wikipedia — MCP Server

> Ground AI answers in verifiable Wikipedia articles — no API key needed.

**Source:** https://mcpplaygroundonline.com/mcp-servers/wikipedia  
**Transport:** stdio  
**Requires auth:** No

---

## What it does

The Wikipedia MCP server exposes the Wikipedia API as a set of read-only MCP tools. Models can search for articles, retrieve the full plain-text of an article, get a short summary, list an article's sections and links, find related topics, and produce query-focused or section summaries and key-fact extracts. It runs as a stdio process and requires no credentials, since Wikipedia's content API is public. Because every answer traces back to a named article, it is a strong grounding source for agents that must stay factual and citeable — pair it with a live web-search server for anything more recent than the encyclopedia.

## Tools exposed

- search_wikipedia — find articles matching a query, with title, snippet and page id
- get_article — retrieve the full plain-text content of an article
- get_summary — get a short summary of an article
- get_sections / get_links — list an article's sections and outbound links
- get_related_topics, summarize_article_for_query, extract_key_facts — targeted research helpers

## Example queries you can run

- "Search Wikipedia for "Model Context Protocol" and summarise what the article says."
- "Get the key facts from the article on the transformer architecture in machine learning."
- "List the sections of the "Large language model" article and tell me which cover training."
- "Find topics related to retrieval-augmented generation and give me a one-line summary of each."

## Details

- **Recommended model:** anthropic/claude-haiku-4.5 — Wikipedia calls are simple lookups, so Claude Haiku 4.5 is fast and cheap. Step up to Sonnet 4.5 when you want the model to synthesise across several articles.
- **Transport:** stdio
- **Authentication:** Not required — No API key required — Wikipedia's content API is public. Deploy a sandboxed hosted instance from the MCP Playground catalog in one click and start querying immediately.
- **Official source:** [Rudra-ravi/wikipedia-mcp on GitHub](https://github.com/Rudra-ravi/wikipedia-mcp)

## Frequently asked questions

### What is the Wikipedia MCP server?

It is an open-source MCP server that gives AI models read access to Wikipedia. It exposes tools to search articles, fetch full text or summaries, list sections and links, and extract key facts — all through the Model Context Protocol, with no API key.

### Which tools does the Wikipedia MCP server expose?

Core tools include search_wikipedia, get_article, get_summary, get_sections, get_links and get_related_topics, plus helpers like summarize_article_for_query and extract_key_facts for query-focused research.

### Does the Wikipedia MCP server need an API key?

No. Wikipedia's content API is public, so the server runs without any credentials. That makes it one of the fastest MCP servers to deploy and test.

### Is Wikipedia content up to date enough for my agent?

Wikipedia is current for encyclopedic topics but not for breaking news or fast-moving data. For recency, pair the Wikipedia server with a live web-search server like Brave, Tavily or Perplexity and let the agent choose the right source.

### How do I test a Wikipedia MCP server in the browser?

Open MCP Agent Studio, deploy the hosted Wikipedia server from the catalog (no key needed), pick a model and ask a question. You can watch each search_wikipedia and get_article call and its result live.

---

_Test this server across 40+ models on MCP Playground: https://mcpplaygroundonline.com/mcp-servers/wikipedia — free, no install._