Currys MCP server for AI agents

Let Claude, ChatGPT or your own agent read Currys: 2 typed functions through one MCP server. No Currys API key needed.

Functions
2
Sign-in
Not needed
Works with
MCP, HTTP, Node, Python

Connect

Just Currys

An MCP server for Currys 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/currys
Every site

One MCP server for Currys and every other site Bowmark covers. Your agent looks up what it needs and calls it.

https://api.bowmark.ai/mcp
Set it up in your client

Both 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
  • listClearanceLists Currys' clearance / outlet / reduced-price deals (its clearance-all category), optionally filtered to one or more product types such as Laptops…

    Arguments

    NameTypeRequired
    productTypesstring[]
    Currys' own filter values, e.g. ["Laptops", "Air fryers"]; omit for all clearance.
    No
    pagenumber
    1-based, 20 listings a page.
    No

    Returns CurrysListing

    interface CurrysProduct {
      id: string;              // Currys product id
      sku: string | null;
      brand: string | null;
      name: string;
      price: number | null;    // current price, GBP
      wasPrice: number | null; // pre-reduction price, only when above price
      currency: string;        // "GBP"
      stockStatus: string | null; // Currys' own word, e.g. "IN_STOCK"
      inStock: boolean | null;
      category: string | null; // e.g. "Windows Laptops and Covertables"
      url: string;
      image: string;
    }
    
    interface CurrysListing {
      url: string;
      total: number | null;    // matches across all pages
      page: number;
      pageSize: number;
      products: CurrysProduct[];
      productTypes: string[];  // every filter value this page offers, valid input to productTypes
    }

    HTTP endpoint

    POST https://api.bowmark.ai/v1/sites/currys/listClearance

    Call it

    import { bowmark } from "@bowmark/web";
    
    const result = await bowmark.providers.currys.listClearance({});

Use it from code