Underpriced AI
Server Details
Ask what a thrift find sells for. Real eBay sold comps, price range and net after fees.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- Underpriced AI
TDQS
Scored across 6 tools
Each tool has a largely distinct role: deal hunting (find_underpriced), raw sold data (get_sold_comps), calibrated valuation (price_item), fee arithmetic (worth_it), async result retrieval (get_scan_result), and draft listing creation (list_on_ebay). The main overlap is between price_item and get_sold_comps (both return sold comps) and between price_item and get_scan_result (same output shape, one synchronous one deferred), which descriptions clarify but still require careful reading.
All names are snake_case and verb-first (find_, get_, list_, price_, worth_), which is a predictable and readable convention. Minor deviations exist: 'find_underpriced' and 'worth_it' omit the resource noun that the other names carry, making the pattern slightly less uniform.
Six tools is tightly scoped for a pricing and eBay-listing assistant, and each one covers a distinct step in the workflow. Nothing looks redundant or padded.
The core lifecycle is covered: comps research, valuation, deal discovery, async scan retrieval, fee math, and draft listing creation, with publishing deliberately deferred to the app. Gaps remain around managing existing listings or inventory (no update, relist, or view-live-listings operation) and no way to manage or list saved scans beyond re-reading a known scanId.
Available Tools
6 toolsfind_underpricedFind eBay listings under marketARead-onlyInspect
Live eBay US Buy It Now listings of an item priced under what the same item actually sells for. Use when the user wants to buy something below market. One search runs, as in get_sold_comps (the query as typed, model or part_number appended when missing; with no query, brand plus model or part number): the recent sold prices give the usual price (soldBaseline: typicalPrice, the range and how many sales), then the live listings for the same words are checked title by title and only the same item is kept (other models, lots and accessories are left out, and for-parts listings unless condition asks for them). A deal's total is price plus shipping when eBay gives shipping; it is at least 15% under the usual price for its condition, or, with max_price, at or under max_price (shipping shown) and at least 5% under the usual price. Up to 10 deals, best discount first, each with title, price, shipping, condition, seller feedback, how far under (say) and the listing link. Prices in USD. When deals carry links, disclosure is a sentence the user must see.
Inputs: brand, model, query, condition, +2 more. Returns: note, text, deals, query, +12 more
get_scan_resultFetch a saved scan's resultARead-onlyIdempotentInspect
For a signed-in user: the finished result for a scan on their account, in the same shape as price_item, once the sold comps have landed in the background. Call it with the account.scanId a photo price returned when that result said comps were still loading (about 20 seconds later), or to re-read any saved scan.
Inputs: scan_id (required), cost. Returns: The same fields as price_item's answer.
get_sold_compsRecent eBay sold compsARead-onlyIdempotentInspect
The most recent real eBay sales (sold comps) for a search query (brand, model or pattern, a few specific words), with the count, median and quartiles. Use when the user wants to see what actually sold and for how much. It searches the signed-in user's own eBay marketplace (eBay UK in GBP for a UK seller), eBay US in USD when nobody is signed in, or the site given in marketplace; the result names the site (marketplace) and the currency (currency). One search runs: the query as typed (a retail price with "$" in it is left out), with model or part_number appended only when the query does not already name it; with no query, brand plus model, or brand plus part_number. Sales whose title shows a different item are left out of the count, median and quartiles: comps.matched is how many were kept, comps.dropped how many were left out, and comps.relevanceChecked is false when that check could not run (every sale is then kept). comps.countIsLowerBound true means eBay returned a full page, so the count is that many or more. include words must all appear in a sale's title (and are added to the search when missing); a title with any exclude word is left out; both match whole words in any case and are named in the answer. prefer words leave nothing out: sales whose title has every one are listed first (preferred true) and summarized in comps.preferred, while count and summary still cover every matching sale. Each listed sale has condition, saleType, bids, shipping and location, each null when not known (a sale stored before 22 October 2026 gives condition only as new or used). exclude_items leaves out sales by eBay item number (each listed sale's itemId), before every other filter; comps.removedByItems counts them. limit sets how many recent sales are listed (default 8, up to 50).
Inputs: brand, limit, model, query, +6 more. Returns: next, note, text, comps, +13 more
list_on_ebayPrepare an eBay listingAIdempotentInspect
For a signed-in user: turns a photo scan from price_item (account.scanId) into an inventory item with a draft eBay listing on their Underpriced AI account (title, list price defaulting to the market price, condition, description) and returns the link where they review and publish it in the app, plus whether eBay is connected and the connect link if not (connecting brings them back to the same item). If the item already has an unpublished eBay draft, it returns that draft unchanged and never overwrites it (draftKept); changes are made in the app. It never publishes anything and only prepares eBay; publishing happens in the app after the user checks the listing, and until then the draft shows in the app under Sell, Not live yet.
Inputs: scan_id (required), price, title, condition.
price_itemPrice an itemAInspect
What a secondhand item sells for on eBay: a calibrated estimate with a range, the recent real eBay sales behind it (sold comps, linked where the source gives a link), three list prices (fast, market, patient) with the 14-day sell chance, what the seller keeps after eBay fees, and a worth-it verdict when you pass what the user would pay. A description price searches the signed-in user's own eBay marketplace (eBay UK in GBP for a UK seller), eBay US in USD when nobody is signed in, or the site given in marketplace; price.currency names the currency. A photo price (photo, a file the user uploaded in the chat, or image_url, a public https link) needs the user signed in through the connector: it runs a real scan on their account, priced in their own eBay marketplace and currency (price.currency). Without sign-in, describe the item; a description works but reads less than a photo.
Inputs: cost, size, brand, model, +6 more. Returns: ask, tip, item, next, +11 more
worth_itWorth buying at this cost?ARead-onlyIdempotentInspect
What the seller keeps after eBay fees and a verdict (worth it / thin / pass) for an expected sale price and what the user would pay. Pure arithmetic in the currency you give it, with eBay US fees: pass the sale price and the cost in the same currency (the one price_item named in price.currency). For a seller on eBay UK, the worthIt block price_item returns already uses their own fees. Use price_item first when the sale price is unknown.
Inputs: cost (required), expected_sale_price (required). Returns: cost, rule, text, label, +5 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Appraise resale items from photos and write listings for eBay, Mercari, OfferUp and more.
Sold comps and active listings from eBay, Poshmark, Mercari, Depop, Vinted, TCGplayer and more.
Know what anything is worth new, used, or resale, and get links to the best place to buy or sell it. Just name it or snap a photo.
90-day eBay & Mercari realized sold prices, Accepted Best Offers, IQR median & net flip profit.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceItemises marketplace fees, shipping, and item costs to work out true net profit, margin, and ROI for sales on eBay, Etsy, Poshmark, Mercari, Depop, Whatnot, and TikTok Shop. It also ranks the same item across all seven platforms and finds the lowest list price that still hits a target profit, with dated fee schedules and custom fee overrides.MIT
- AlicenseAqualityDmaintenanceSearch eBay and get real price data, straight from an AI agent.31MIT
- AlicenseNot gradedqualityCmaintenanceEnables search of Poshmark's public marketplace for sold and active listings, returning detailed comp data such as price, size, brand, condition, sold date, seller, and listing URLs—no login or API key required.73 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables users to fetch 90-day realized eBay and Mercari sold prices, valuation and spread metrics, sell-through rates, fee-adjusted flip profit, and underpriced-deal alerts through MCP.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.