Wikipedia article summary lookup by title or query. x402 per call.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
$0.01 via x402: Wikipedia knowledge lookup — article titles, extract snippets and canonical URLs for any topic. The cheap fact-grounding read agents make to reduce hallucination. Free upstream (Wikimedia).
Topic / search query
Results 1-10 (default 3)
x402 payment payload (base64) to settle this call; omit to receive the payment terms first
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http wikipedia-lookup 'https://store.agentexchange.work/research/mcp?tools=wikipedia_lookup'
$0.01 via x402: Wikipedia knowledge lookup — article titles, extract snippets and canonical URLs for any topic. The cheap fact-grounding read agents make to reduce hallucination. Free upstream (Wikimedia).
| Argument | Type | Description |
|---|
| q* | string | Topic / search query |
| limit | number | Results 1-10 (default 3) |
| x_payment | string | x402 payment payload (base64) to settle this call; omit to receive the payment terms first |
{
"type": "object",
"required": [
"q"
],
"properties": {
"q": {
"type": "string",
"description": "Topic / search query"
},
"limit": {
"type": "number",
"description": "Results 1-10 (default 3)"
},
"x_payment": {
"type": "string",
"description": "x402 payment payload (base64) to settle this call; omit to receive the payment terms first"
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 20, 2026.