search
Pack: serper · Connect: https://pipeworx.io/mcp (see Connect below for a single-pack URL)
No MCP client? Call it directly: GET https://gateway.pipeworx.io/v1/tools/search for the schema, then POST the same URL with its arguments for the data.
Google web search via Serper: returns organic results (title, link, snippet, position), an answer box if present, and a knowledge graph summary. Accepts query, result count (max 20), and optional country code (gl) and location for geo-targeted results.
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
query | string | yes | Search query, e.g. “best espresso machine 2026” |
num | number | no | Number of results (default 10, max 20) |
gl | string | no | Country code for geolocation, e.g. “us”, “gb”, “de” |
location | string | no | Location string, e.g. “San Francisco, California, United States” |
Example call
Arguments
{
"query": "best espresso machine 2026",
"num": 10,
"_apiKey": "your-serper-api-key"
}
curl
curl -X POST https://gateway.pipeworx.io/serper/mcp \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"search","arguments":{"query":"best espresso machine 2026","num":10,"_apiKey":"your-serper-api-key"}}}'
TypeScript (@pipeworx/sdk)
import { Pipeworx } from '@pipeworx/sdk';
const pipeworx = new Pipeworx();
const result = await pipeworx.call('search', {
"query": "best espresso machine 2026",
"num": 10,
"_apiKey": "your-serper-api-key"
});
More examples
{
"query": "python machine learning libraries",
"num": 15,
"gl": "us",
"location": "San Francisco, California, United States",
"_apiKey": "your-serper-api-key"
}
Connect
Add this to your MCP client config — every tool in the catalog, including this one — or use one-click install buttons:
{
"mcpServers": {
"pipeworx": {
"url": "https://pipeworx.io/mcp"
}
}
}
Connect to just the serper pack
{
"mcpServers": {
"serper": {
"url": "https://gateway.pipeworx.io/serper/mcp"
}
}
}
See Getting Started for client-specific install steps.