Parts Geek MCP server for AI agents
Let Claude, ChatGPT or your own agent read Parts Geek: 2 typed functions through one MCP server. No Parts Geek API key needed.
- Site
- partsgeek.com
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Parts Geek
An MCP server for Parts Geek 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/partsgeekEvery site
One MCP server for Parts Geek 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
getMakeCatalogLists the vehicle models and part categories Parts Geek carries for one vehicle make, read off the make's own page (/makes/<make>.html).Arguments
Name Type Required arg0{ make: string }Yes Returns
PartsgeekMakeCataloginterface PartsgeekMakeCatalog { make: string; title: string; url: string; models: { name: string; slug: string; url: string }[]; partCategories: { name: string; slug: string; url: string }[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/partsgeek/getMakeCatalogCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.partsgeek.getMakeCatalog({ make: "Honda" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.partsgeek.getMakeCatalog({"make": "Honda"}))curl -X POST https://api.bowmark.ai/v1/sites/partsgeek/getMakeCatalog \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"arg0":{"make":"Honda"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.partsgeek.getMakeCatalog({ make: "Honda" });searchPartsSearches Parts Geek's auto-parts catalog through its own search page (/ss/?ssq=), returning each part's title, vehicle, price, brand, part number…Arguments
Name Type Required arg0{ query: string; page?: number }Yes Returns
PartsgeekSearchResultinterface PartsgeekPart { title: string; vehicle: string | null; partNumber: string | null; brand: string | null; price: number | null; stock: string | null; freeShipping: boolean; notes: string | null; attributes: Record<string, string>; fits: string[]; productId: string | null; imageUrl: string | null; } interface PartsgeekSearchResult { query: string; page: number; hasNextPage: boolean; parts: PartsgeekPart[]; url: string }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/partsgeek/searchPartsCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.partsgeek.searchParts({ query: "brake pads" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.partsgeek.searchParts({"query": "brake pads"}))curl -X POST https://api.bowmark.ai/v1/sites/partsgeek/searchParts \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"arg0":{"query":"brake pads"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.partsgeek.searchParts({ query: "brake pads" });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/partsgeek/<function> - OpenAPI
/v1/sites/partsgeek/openapi.json