OTTO MCP server for AI agents
Let Claude, ChatGPT or your own agent read OTTO: 2 typed functions through one MCP server. No OTTO API key needed.
- Site
- otto.de
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just OTTO
An MCP server for OTTO 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/ottoEvery site
One MCP server for OTTO 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 OTTO product page.Arguments
Name Type Required urlstringYes Returns
ottoProductinterface ottoProduct { productId: string; variationId: string | null; sku: string; gtin13: string | null; name: string; description: string; brand: string; url: string; price: number; originalPrice: number | null; discountPercent: number | null; currency: string; availability: string | null; // the site's own labels, read the values off a result, never guess one from prose soldOut: boolean; delivery: { text: string; minDays: number | null; maxDays: number | null } | null; rating: { value: number; count: number } | null; images: string[]; sizes: { label: string; selected: boolean; available: boolean }[]; colors: { label: string; selected: boolean; available: boolean; image: string | null }[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/otto/getProductCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.otto.getProduct("<url>");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.otto.getProduct("<url>"))curl -X POST https://api.bowmark.ai/v1/sites/otto/getProduct \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"url":"<url>"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.otto.getProduct("<url>");searchSearches OTTO's catalog for a keyword the way the site's own search bar does, across its whole marketplace (fashion, furniture, electronics, pet…Arguments
Name Type Required querystringYes limitnumberNo Returns
ottoSearchResult[]interface ottoSearchPrice { currentAmount: number; currentDisplay: string; suggestedRetailAmount: number | null; suggestedRetailDisplay: string | null; comparativeAmount: number | null; comparativeDisplay: string | null; onSale: boolean; isStartingPrice: boolean; } interface ottoSearchResult { productId: string; variationId: string; articleNumber: string; url: string; name: string; brand: string; price: ottoSearchPrice; availability: { state: string; detail: string }; thumbnail: string | null; rating: { value: number; count: number } | null; matchType: string; totalCount: number; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/otto/searchCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.otto.search({ query: "schuhe" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.otto.search({"query": "schuhe"}))curl -X POST https://api.bowmark.ai/v1/sites/otto/search \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"query":{"query":"schuhe"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.otto.search({ query: "schuhe" });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/otto/<function> - OpenAPI
/v1/sites/otto/openapi.json