Gazelle MCP server for AI agents
Let Claude, ChatGPT or your own agent read Gazelle: 2 typed functions through one MCP server. No Gazelle API key needed.
- Site
- gazelle.com
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Gazelle
An MCP server for Gazelle 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/gazelleEvery site
One MCP server for Gazelle 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
findDevicesEvery device gazelle.com takes in trade, off gazelle's own sitemap.Arguments
Name Type Required querystringNo Returns
GazelleDevice[]interface GazelleDevice { name: string; // "iPhone 14 Pro", what a person would say brand: string; // gazelle's own brand segment, e.g. "iphone" model: string; // gazelle's own model slug, e.g. "iphone-14-pro" url: string; // the device's trade-in page }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/gazelle/findDevicesCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.gazelle.findDevices("iphone");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.gazelle.findDevices("iphone"))curl -X POST https://api.bowmark.ai/v1/sites/gazelle/findDevices \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"query":"iphone"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.gazelle.findDevices("iphone");getTradeInQuoteReads gazelle.com's own current trade-in offer for a device named by NAME or by URL (capacity/carrier/condition), off the same bootstrap JSON and…Arguments
Name Type Required devicestringYes selections{ capacity?: string; carrier?: string; condition?: string }No Returns
GazelleQuoteResultinterface GazelleQuoteResult { deviceUrl: string; product: { id: string; name: string }; selections: { capacity: string | null; carrier: string | null; condition: string | null }; estimatedValue: number; expirationDate: string | null; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/gazelle/getTradeInQuoteCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.gazelle.getTradeInQuote("<device>");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.gazelle.getTradeInQuote("<device>"))curl -X POST https://api.bowmark.ai/v1/sites/gazelle/getTradeInQuote \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"device":"<device>"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.gazelle.getTradeInQuote("<device>");
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/gazelle/<function> - OpenAPI
/v1/sites/gazelle/openapi.json