Ferguson MCP server for AI agents
Let Claude, ChatGPT or your own agent read Ferguson: 2 typed functions through one MCP server. No Ferguson API key needed.
- Site
- ferguson.com
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Ferguson
An MCP server for Ferguson 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/fergusonEvery site
One MCP server for Ferguson 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 2
findBranchesLists Ferguson branch locations in a US state, optionally narrowed by city and by branch line (plumbing/PVF, HVAC, waterworks, warehouse…Arguments
Name Type Required statestringTwo-letter US code.Yes citystringNo typestringSubstring of the branch line, e.g. "hvac".No Returns
fergusonBranch[]interface fergusonBranch { state: string; // "VA" city: string; // "falls church" type: string; // "plumbingpvf" | "hvac" | "waterworks" | "warehouse" | "mechanicalindustrial" | "firefabrication" | … branchNumber: string; url: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/ferguson/findBranchesCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.ferguson.findBranches({ state: "VA" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.ferguson.findBranches({"state": "VA"}))curl -X POST https://api.bowmark.ai/v1/sites/ferguson/findBranches \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"state":"VA"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.ferguson.findBranches({ state: "VA" });findProductsFinds Ferguson catalog products (plumbing, HVAC, PVF, waterworks, appliances) whose title contains every word of a keyword query.Arguments
Name Type Required querystringEvery word must appear in the title, e.g. "kohler pot filler".Yes limitnumberDefault 20, max 100.No Returns
fergusonProduct[]interface fergusonProduct { productId: string; // Ferguson's own id, the <id>.html in the url title: string; // url slug as words: product title + manufacturer part number url: string; lastModified: string | null; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/ferguson/findProductsCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.ferguson.findProducts({ query: "pot filler", limit: 3 });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.ferguson.findProducts({"query": "pot filler", "limit": 3}))curl -X POST https://api.bowmark.ai/v1/sites/ferguson/findProducts \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"query":"pot filler","limit":3}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.ferguson.findProducts({ query: "pot filler", limit: 3 });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/ferguson/<function> - OpenAPI
/v1/sites/ferguson/openapi.json