ebay-mcp
Allows searching active eBay listings, analyzing price distributions, finding deals priced below market median, and performing market research using eBay's Buy Browse API.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
ebay-mcp
Expose eBay's marketplace to Claude over the Model Context Protocol. Claude can search active listings, analyse price distributions, surface deals priced below the market median, and produce a market-research overview — all as structured JSON it can reason about.
It answers questions like:
What does a used Nintendo Switch OLED actually sell for right now?
Find me listings priced well below the going rate.
Give me a market overview: price spread, condition mix, who's selling, and shipping.
How it works
OAuth2 (client credentials)
│
┌────────┐ tools ┌──────┴───────┐ HTTPS ┌──────────────────┐
│ Claude │ ────────► │ ebay-mcp │ ────────► │ eBay Buy Browse │
│ │ ◄──────── │ MCP server │ ◄──────── │ API │
└────────┘ JSON └──────────────┘ └──────────────────┘The server authenticates to eBay with the OAuth2 client-credentials grant (caching and refreshing the application token), calls the Buy Browse API, normalises the verbose responses into typed objects, and runs price/market analysis locally before handing JSON back to Claude.
The code is layered so the analysis is testable without the network:
config.py— environment-driven configuration.models.py— typed value objects parsed from eBay JSON.auth.py— OAuth token caching/refresh (concurrency-safe).client.py— the only module that talks to eBay; retries + filter grammar.analysis.py— pure price/deal/market functions.server.py— the MCP tools.
Related MCP server: eBay MCP Server
Tools
Tool | What it does |
| Search active listings (sort, condition, price range, free-shipping filters). |
| Price distribution for a query: min/max, mean, median, p25/p75/p90, stdev. |
| Listings priced at least N% below the market median, ranked by discount. |
| Full overview: price stats, condition mix, price-by-condition, shipping, seller locations, observations. |
| Full details for a single listing by item id. |
All prices are isolated to a single currency and, unless noted, reflect total cost (item + shipping).
Setup
Requires Python 3.10+ and an eBay developer account.
Create an application at https://developer.ebay.com/my/keys and copy the App ID (Client ID) and Cert ID (Client Secret).
Install:
git clone https://github.com/luke-nielsen/ebay-mcp.git cd ebay-mcp python3 -m venv .venv && source .venv/bin/activate pip install -e ".[dev]"Configure credentials (copy
.env.exampleto.env, or export directly):export EBAY_CLIENT_ID=your-app-id export EBAY_CLIENT_SECRET=your-cert-idVerify connectivity:
ebay-mcp check ebay-mcp search "nintendo switch oled" --limit 5 ebay-mcp research "airpods pro 2"
Connecting to Claude
Add the server to your MCP host. For Claude Code:
claude mcp add ebay -- ebay-mcp serveOr use the bundled .mcp.json (it reads EBAY_CLIENT_ID / EBAY_CLIENT_SECRET
from your environment). The server speaks MCP over stdio.
Configuration
Variable | Default | Description |
| — | App ID (Client ID). Required. |
| — | Cert ID (Client Secret). Required. |
|
|
|
|
| e.g. |
| — | Buyer country for shipping estimates. |
| — | Buyer postal code for shipping estimates. |
|
| Per-request timeout (seconds). |
|
| Retry attempts for transient failures. |
Development
pip install -e ".[dev]"
pytest # run the test suite
ruff check . # lintThe networking layer is exercised with httpx.MockTransport, so the full suite
runs offline and needs no credentials.
Notes & limitations
Uses the Buy Browse API, which covers active listings. Sold/completed price history requires eBay's restricted Marketplace Insights API and is out of scope here; "market" statistics are therefore over current asking prices.
The client-credentials token grants access to public search only — no user-specific or order data.
eBay rate limits the Browse API (default ~5,000 calls/day); the analysis tools spend one call each.
License
MIT — see LICENSE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Search eBay sold and active listings, browse categories, and retrieve item details.
Live eBay prices, sellers and profit for any keyword on 8 eBay sites. Pay per call with x402 USDC.
CompSniper gives AI assistants real eBay sold prices: up to 240 sold listings per call, 3 years (1,095 days) of eBay sold history on every plan including free, and the real accepted Best Offer price (what the buyer actually paid). 18 marketplaces on one key: 8 eBay sites (US, UK, Germany, France, Italy, Spain, Canada, Australia) plus TCGplayer, PSA, Grailed, Poshmark, Mercari, Depop and the Goldin, Fanatics Collect, Pristine Auction and MySlabs auction houses. Results come raw or AI-cleaned (accessories, lots and wrong models removed), with median, range and shipping. Free plan: 100 requests a month, no card. In the Claude Connectors Directory and ChatGPT Plugins.
Live eBay market intelligence: underpriced listing scans, price distributions, flip margins.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that lets you fetch auctions from Ebay.com using natural language prompts like 'Find me 10 auctions for batman comics'.15MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to search eBay listings, track item prices over time, and identify deals below market value using eBay's APIs. It provides tools for category browsing and retrieving detailed information for specific listings.1MIT
- AlicenseAqualityDmaintenanceSearch eBay and get real price data, straight from an AI agent.31MIT
- AlicenseAqualityDmaintenanceEnables AI agents to search products, view item details, track and place bids, make Buy It Now purchases, view order history, and track shipments on eBay via browser automation with Playwright.7MIT