GlassesUSA MCP server for AI agents
Let Claude, ChatGPT or your own agent read GlassesUSA: 2 typed functions through one MCP server. No GlassesUSA API key needed.
- Site
- glassesusa.com
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just GlassesUSA
An MCP server for GlassesUSA 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/glassesusaEvery site
One MCP server for GlassesUSA 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 product's own page.Arguments
Name Type Required urlstringYes Returns
GlassesusaProductinterface GlassesusaProduct { url: string; title: string; price: number | null; // real, current selling price, USD wasPrice: number | null; // the crossed-out "was" price, when shown currency: string; rating: number | null; reviewCount: number | null; vtoAvailable: boolean; // GlassesUSA's own Virtual Try-On is offered prescriptionEligible: boolean; // orderable with prescription lenses }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/glassesusa/getProductCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.glassesusa.getProduct("<url>");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.glassesusa.getProduct("<url>"))curl -X POST https://api.bowmark.ai/v1/sites/glassesusa/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.glassesusa.getProduct("<url>");searchRuns GlassesUSA's own catalog search and returns matching frames with their live selling price.Arguments
Name Type Required querystringYes Returns
GlassesusaSearchResult[]interface GlassesusaSearchResult { url: string; title: string; price: number; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/glassesusa/searchCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.glassesusa.search("ray-ban");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.glassesusa.search("ray-ban"))curl -X POST https://api.bowmark.ai/v1/sites/glassesusa/search \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"query":"ray-ban"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.glassesusa.search("ray-ban");
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/glassesusa/<function> - OpenAPI
/v1/sites/glassesusa/openapi.json