`find_similar`

Pack: exa · 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/find_similar for the schema, then POST the same URL with its arguments for the data.

Find pages similar to a given URL using neural/semantic matching. Returns title, URL, relevance score, and published date. Example: find_similar({ url: “https://example.com/great-article”, num_results: 10 })

Parameters

Name	Type	Required	Description
`url`	string	yes	The URL to find semantically similar pages for.
`num_results`	number	no	Number of results to return (default 10, max 25)
`_apiKey`	string	no	Optional — your own Exa API key for higher limits; omit to use the shared Pipeworx key.

Example call

Arguments

{
  "url": "https://example.com/great-article",
  "num_results": 10
}

curl

curl -X POST https://gateway.pipeworx.io/exa/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"find_similar","arguments":{"url":"https://example.com/great-article","num_results":10}}}'

TypeScript (@pipeworx/sdk)

import { Pipeworx } from '@pipeworx/sdk';
const pipeworx = new Pipeworx();

const result = await pipeworx.call('find_similar', {
  "url": "https://example.com/great-article",
  "num_results": 10
});

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 exa pack

{
  "mcpServers": {
    "exa": {
      "url": "https://gateway.pipeworx.io/exa/mcp"
    }
  }
}

See Getting Started for client-specific install steps.

find_similar