Smartwool MCP server for AI agents
Let Claude, ChatGPT or your own agent read Smartwool: 1 typed function through one MCP server. No Smartwool API key needed.
- Site
- smartwool.com
- Functions
- 1
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Smartwool
An MCP server for Smartwool alone, with one tool per function. Paste it into Claude, ChatGPT, Cursor or any MCP client as a remote server.
https://api.bowmark.ai/mcp/site/smartwoolEvery site
One MCP server for Smartwool and every other site Bowmark covers. Your agent looks up what it needs and calls it.
https://api.bowmark.ai/mcpSet it up in your clientBoth need a Bowmark API key. The quickstart gets you one and a first result in a few minutes.
Functions
Open a function to see its arguments, what it returns and how to call it.
Read 1
getSockRecommendationRuns Smartwool's own Sock Finder quiz with the given answers and returns the socks it recommends, the same result a shopper would see, no email…Arguments
Name Type Required activitystringYes typestringYes sockHeightstringYes cushionstringYes stylestringYes sizestringYes Returns
SmartwoolSockFinderResultinterface SmartwoolRecommendedProduct { title: string; price: number | null; // USD rating: number | null; // out of 5 url: string | null; image: string | null; sku: string | null; score: number | null; // the quiz's match score, 0-100 } interface SmartwoolSockFinderResult { headline: string; description: string; selections: { activity: string | null; type: string | null; sockHeight: string | null; cushion: string | null; style: string | null; size: string | null; }; // Questions this answer path never asks; those arguments were ignored. skipped: ("activity" | "type" | "sockHeight" | "cushion" | "style" | "size")[]; recommendations: SmartwoolRecommendedProduct[]; pairings: SmartwoolRecommendedProduct[]; shopLinks: { label: string; ariaLabel: string; url: string | null }[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/smartwool/getSockRecommendationCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.smartwool.getSockRecommendation("Everyday Life", "Men's", "No Show", "Zero Cushion", "Solid", "S 3 - 5.5");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.smartwool.getSockRecommendation("Everyday Life", "Men's", "No Show", "Zero Cushion", "Solid", "S 3 - 5.5"))curl -X POST https://api.bowmark.ai/v1/sites/smartwool/getSockRecommendation \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"activity":"Everyday Life","type":"Men'\''s","sockHeight":"No Show","cushion":"Zero Cushion","style":"Solid","size":"S 3 - 5.5"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.smartwool.getSockRecommendation("Everyday Life", "Men's", "No Show", "Zero Cushion", "Solid", "S 3 - 5.5");
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/smartwool/<function> - OpenAPI
/v1/sites/smartwool/openapi.json