Article MCP server for AI agents
Let Claude, ChatGPT or your own agent read Article: 2 typed functions through one MCP server. No Article API key needed.
- Site
- article.com
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Article
An MCP server for Article 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/article_comEvery site
One MCP server for Article 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
getProductReads one Article product by id or article.com URL: USD and CAD list price and sale price, stock and sale/clearance state, overall dimensions, the…Arguments
Name Type Required productIdstringYes Returns
ArticleProductinterface ArticlePrice { currency: string; price: number; salePrice: number | null } interface ArticleProduct { productId: string; sku: string; title: string; url: string; status: string; active: boolean; inStock: boolean; onSale: boolean; onClearance: boolean; description: string | null; collection: string | null; category: string | null; finish: string | null; prices: ArticlePrice[]; dimensions: { height: string | null; width: string | null; depth: string | null }; specs: { key: string; value: string }[]; features: string[]; care: string[]; rating: number | null; reviewCount: number | null; images: string[]; variants: { productId: string; sku: string; finish: string | null; title: string }[]; assemblyInstructionsUrl: string | null; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/article_com/getProductCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.article_com.getProduct("26945");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.article_com.getProduct("26945"))curl -X POST https://api.bowmark.ai/v1/sites/article_com/getProduct \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"productId":"26945"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.article_com.getProduct("26945");searchProductsSearches Article's furniture catalog by free text.Arguments
Name Type Required argsArticleSearchArgsYes interface ArticleSearchArgs { query: string; limit?: number /* 1-48, default 24 */; country?: "US" | "CA" }Returns
ArticleSearchResultinterface ArticleSearchRow { productId: string; sku: string; title: string; price: number | null; url: string; imageUrl: string | null; isBundle: boolean } interface ArticleSearchResult { query: string; totalGroups: number; products: ArticleSearchRow[] }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/article_com/searchProductsCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.article_com.searchProducts({ query: "sofa", limit: 5 });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.article_com.searchProducts({"query": "sofa", "limit": 5}))curl -X POST https://api.bowmark.ai/v1/sites/article_com/searchProducts \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"query":"sofa","limit":5}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.article_com.searchProducts({ query: "sofa", limit: 5 });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/article_com/<function> - OpenAPI
/v1/sites/article_com/openapi.json