Mercari MCP server for AI agents
Let Claude, ChatGPT or your own agent read Mercari: 1 typed function through one MCP server. No Mercari API key needed.
- Site
- mercari.com
- Functions
- 1
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Mercari
An MCP server for Mercari 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/mercariEvery site
One MCP server for Mercari 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 1
searchRuns a Mercari US keyword search the way mercari.com's own search box does and returns the matching listings.Arguments
Name Type Required querystring | { query: string; limit?: number }Yes Returns
MercariSearchResult[]interface MercariSearchResult { itemId: string; name: string; price: number; wasPrice: number | null; brand: string | null; size: string | null; url: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/mercari/searchCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.mercari.search("jacket");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.mercari.search("jacket"))curl -X POST https://api.bowmark.ai/v1/sites/mercari/search \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"query":"jacket"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.mercari.search("jacket");
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/mercari/<function> - OpenAPI
/v1/sites/mercari/openapi.json