Fortress Building Products MCP server for AI agents
Let Claude, ChatGPT or your own agent read Fortress Building Products: 2 typed functions through one MCP server. No Fortress Building Products API key needed.
- Site
- fortressbp.com
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Fortress Building Products
An MCP server for Fortress Building Products 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/fortressbpEvery site
One MCP server for Fortress Building Products 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
listProductTypesReads the live Simplifinder form on /about/plan-your-project and returns its top-level product-type choices (Fencing / Framing / Pergolas), the entry…Arguments
None.
Returns
ListProductTypesResultinterface ListProductTypesResult { productTypes: string[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/fortressbp/listProductTypesCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.fortressbp.listProductTypes();import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.fortressbp.listProductTypes())curl -X POST https://api.bowmark.ai/v1/sites/fortressbp/listProductTypes \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.fortressbp.listProductTypes();recommendProductWalks Fortress's own Simplifinder decision tree (product type, then application and material where the tree asks for them) with an ordered list of…Arguments
Name Type Required selectionsstring[]Yes Returns
fortressbpRowinterface fortressbpRecommendation { productName: string | null; imageUrl: string; path: string[]; } interface fortressbpNextQuestion { prompt: string; options: string[]; } type fortressbpRow = | ({ complete: true } & fortressbpRecommendation) | ({ complete: false } & fortressbpNextQuestion);HTTP endpoint
POST https://api.bowmark.ai/v1/sites/fortressbp/recommendProductCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.fortressbp.recommendProduct({ selections: ["Framing"] });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.fortressbp.recommendProduct({"selections": ["Framing"]}))curl -X POST https://api.bowmark.ai/v1/sites/fortressbp/recommendProduct \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"selections":["Framing"]}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.fortressbp.recommendProduct({ selections: ["Framing"] });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/fortressbp/<function> - OpenAPI
/v1/sites/fortressbp/openapi.json