Search with Wikimedia

wikimedia

Try it API

Wikimedia searches Wikipedia, with each article’s text from Wikimedia Enterprise.

Features2

Modes1

Filters2

Playground

Pinned to Wikimedia.

Results from Wikimedia

1
List of languages by total number of speakers en.wikipedia.org
2
List of languages by number of native speakers in India en.wikipedia.org
3
Languages of the United States en.wikipedia.org
4
English language en.wikipedia.org
5
Near-native speaker en.wikipedia.org

Recorded from live searches on 28 October 2026.

Features

Wikimedia delivers 2 of the features on the feature list, each from one or more of its modes.

Feature	Returns
Page text	The text of pages: the pages a query finds, read in full or as the passages that answer it, or the pages at given addresses.
Encyclopedia	Encyclopedia articles on a subject, read from Wikipedia's licensed copy.

Modes

Wikimedia has 1 search mode. Choose which of them a search may use under Routing on your account page.

Default search

Filters Wikimedia applies

Set them under filters. A filter a provider can’t apply returns 400 unsupported_filter.

Filter	Keeps
`domains`	Only these sites, or with `"mode": "exclude"`, none of them.
`language`	One language, by its code.

request.jsonJSON

{
  "query": "which language has the most native speakers",
  "top_k": 5,
  "requested_provider": "wikimedia",
  "filters": {
    "domains": { "values": ["en.wikipedia.org"] }
  }
}

Pin a query to Wikimedia

Over the HTTP API, send "requested_provider": "wikimedia" with the query and your search key.
In an agent connected over MCP, ask it to search with Wikimedia.

Results come back in the same shape for every provider, as the docs describe. Leave the field out, and Grounder routes each query to the provider most likely to answer it well.

search.shShell

curl https://api.grounder.net/v1/search \
  -H "Authorization: Bearer $GROUNDER_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "which language has the most native speakers",
    "top_k": 5,
    "requested_provider": "wikimedia"
  }'

import os
import httpx

KEY = os.environ["GROUNDER_KEY"]

r = httpx.post(
    "https://api.grounder.net/v1/search",
    headers={"Authorization": f"Bearer {KEY}"},
    json={
        "query": "which language has the most native speakers",
        "top_k": 5,
        "requested_provider": "wikimedia",
    },
    timeout=30,
).json()

for hit in r["results"]:
    print(hit["rank"], hit["title"], hit["url"])

const res = await fetch("https://api.grounder.net/v1/search", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.GROUNDER_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    query: "which language has the most native speakers",
    top_k: 5,
    requested_provider: "wikimedia",
  }),
})

const { results } = await res.json()

claude mcp add --transport http grounder \
  https://api.grounder.net/mcp
# then /mcp, grounder, Authenticate