Spirit Halloween MCP server for AI agents
Let Claude, ChatGPT or your own agent read Spirit Halloween: 2 typed functions through one MCP server. No Spirit Halloween API key needed.
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Spirit Halloween
An MCP server for Spirit Halloween 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/spirithalloweenEvery site
One MCP server for Spirit Halloween 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 page's full live variant matrix.Arguments
Name Type Required args{ url: string }Yes Returns
SpiritHalloweenProductinterface SpiritHalloweenSizeVariant { color: string size: string // the site's own size label, e.g. "CHILD MEDIUM" price: number inStock: boolean shipStockQuantity: number variantId: string } interface SpiritHalloweenProduct { productId: string name: string url: string sizes: SpiritHalloweenSizeVariant[] // every real color/size combination, each with its own live stock }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/spirithalloween/getProductCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.spirithalloween.getProduct({});import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.spirithalloween.getProduct({}))curl -X POST https://api.bowmark.ai/v1/sites/spirithalloween/getProduct \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.spirithalloween.getProduct({});searchBrowses Spirit Halloween's category listing for a query resolved against a small internal directory of mapped categories (today: "KPop Demon Hunters"…Arguments
Name Type Required args{ query: string; limit?: number }Yes Returns
SpiritHalloweenSearchResultsinterface SpiritHalloweenSearchResult { productId: string sku: string name: string url: string image: string | null price: number | null currency: "USD" listedSize: string | null // the ONE size this listing row is indexed under listedSizeStock: number | null // that size's stock only, not the full range } interface SpiritHalloweenSearchResults { query: string category: string results: SpiritHalloweenSearchResult[] totalMatches: number | null }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/spirithalloween/searchCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.spirithalloween.search({ query: "kpop demon hunters" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.spirithalloween.search({"query": "kpop demon hunters"}))curl -X POST https://api.bowmark.ai/v1/sites/spirithalloween/search \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"query":"kpop demon hunters"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.spirithalloween.search({ query: "kpop demon hunters" });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/spirithalloween/<function> - OpenAPI
/v1/sites/spirithalloween/openapi.json