https://underpricedai.com/api/mcp ↗
Resale prices for secondhand items from real eBay sold listings, with comps and a worth-it verdict.
Underpriced AI is a remote MCP server published at underpricedai.com. It has been probed 13 times since 9/12/2026. It answered in 13 of them (100.0%), a near-uninterrupted record. Median response time is 996 ms, a delay an agent will notice. It offers a narrow, focused set of 6 tools. On the protocol side it speaks the 2026-07-28 stateless spec.
Can an LLM agent pick the right tool here — names, descriptions and parameter clarity are assessed.
price_item — Parameters like 'cost' and 'image_url' have unclear required statusget_scan_result — No error handling for invalid scan_id mentionedlist_on_ebay — Parameter 'price' is optional but critical for listing creationbuy_credits — Incomplete description of payment flow for 'pay as you go' optionRisk: low
tools/list structure, inputSchema validity, and a functional smoke test — the components of the 0-100 score.
Tools the server advertised in the latest measurement — measured, not catalog-claimed.
price_itemWhat a secondhand item sells for on eBay US: a calibrated estimate with a range, the recent real sold comps behind it, three list prices (fast, market, patient) with the 14-day sell chance, the net after eBay fees, and a worth-it verdict when you pass what the user would pay. Give image_url (a public https link to a photo) whenever one exists; a description alone works but reads less.
descriptionstringimage_urlstringconditionstringcostnumberget_sold_compsThe most recent real eBay US sales 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.
querystringrequiredworth_itNet after eBay fees and a verdict (worth it / thin / pass) for an expected sale price and what the user would pay. Pure arithmetic; use price_item first when the sale price is unknown.
expected_sale_pricenumberrequiredcostnumberrequiredbuy_creditsWays to pay for Underpriced AI scans. Without a choice it lists the credit packs (credits never expire), pay as you go ($0.25 per photo scan on a monthly bill, no cap), and for a signed-in user their balance. With a pack it returns a Stripe Checkout link for that user; with PAY_AS_YOU_GO it returns the link that puts a card on file so scans just run from then on. Anonymous callers get the pricing page link.
packstringget_scan_resultFor 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.
scan_idstringrequiredcostnumberlist_on_ebayFor 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. It never publishes anything; publishing happens in the app after the user checks the listing.
scan_idstringrequiredpricenumberconditionstringtitlestringDerived by comparing consecutive probes — changes in era, protocol version, build and reachability.
Add this badge to your README — it updates automatically as measurements change.
[](https://mcpmetrics.io/servers/com-underpricedai-underpriced-ai)<a href="https://mcpmetrics.io/servers/com-underpricedai-underpriced-ai"><img src="https://mcpmetrics.io/badge/com.underpricedai/underpriced-ai/era.svg" alt="mcpmetrics"></a>You are seeing the last 7 days. Sign up for the full history. Which check failed and why is in the dashboard.
Sign up free to seeThe catalog entries whose name and description are closest to this one, found with the same index the search box uses.
GDPR-clean secondhand listings and sold comps for resale pricing research. No seller personal data.
Turn a US address or parcel number into an interactive 3D flyover listing in about a minute.
Model the realistic monthly cost of an LLM app **before you build it**. Not a token calculator: retries, prompt caching, batch discounts, infra overhead, and 3×/10× growth are modeled in, across GPT-5.x, Claude, Gemini, DeepSeek, and more. **Works without a key.** Connect and ask — demo mode covers the six free-tier models. A Pro API key ([beforeyouship.dev](https://beforeyouship.dev)) unlocks the full 18-model catalog. ## Tools | Tool | What it does | |---|---| - **`estimate_cost`** Full cost model for an architecture at a given usage level. Returns Naive / Realistic / Worst Case $/mo per model, growth scenarios, and an opinionated recommendation. | - **`get_model_prices`** Current per-1M-token pricing (input, output, cached, batch) with context windows and staleness metadata. | - **`list_archetypes`** Seven preset architecture patterns (chatbot, RAG pipeline, multi-step agent, …) used as starting points for estimates. | ## Try it Paste into Claude Code or Cursor after connecting
Yapp turns "build me a page and publish it" into a live URL. Connect once (browser OAuth, or a token for terminal clients) and your AI can publish a webpage from HTML, or host a PDF, image, or ZIP exactly as-is to a public `<slug>.yapp.page` URL in seconds, then update, password-protect, set expiry, attach a custom domain, or read form submissions, all by asking. Free to start; no local install. **Tools (15):** `publish_page`, `publish_file`, `update_page`, `delete_page`, `get_page_stats`, `list_my_pages`, `rename_page`, `change_page_slug`, `set_page_expiry`, `set_page_password`, `list_submissions`, `add_custom_domain`, `list_custom_domains`, `check_custom_domain`, `remove_custom_domain`.
| Run | Era | Modern | ms | Legacy | ms | Versions |
|---|---|---|---|---|---|---|
| 2026-09-13 16:52:42 | Dual-era | 200 | 600 | 200 | 646 | 2026-07-28 |
| 2026-09-13 14:49:35 | Dual-era | 200 | 632 | 200 | 639 | 2026-07-28 |
| 2026-09-13 12:47:19 | Dual-era | 200 | 784 | 200 | 878 | 2026-07-28 |
| 2026-09-13 10:45:14 | Dual-era | 200 | 852 | 200 | 868 | 2026-07-28 |
| 2026-09-13 08:43:04 | Dual-era | 200 | 683 | 200 | 1193 | 2026-07-28 |
| 2026-09-13 06:40:42 | Dual-era | 200 | 812 | 200 | 698 | 2026-07-28 |
| 2026-09-13 04:35:29 | Dual-era | 200 | 1218 | 200 | 1320 | 2026-07-28 |
| 2026-09-13 01:33:33 | Dual-era | 200 | 845 | 200 | 842 | 2026-07-28 |
| 2026-09-12 23:31:36 | Dual-era | 200 | 1102 | 200 | 1715 | 2026-07-28 |
| 2026-09-12 21:29:15 | Dual-era | 200 | 1191 | 200 | 1161 | 2026-07-28 |
Each block is one measurement round. Green: working response. Amber: responded but the server was returning errors (5xx). Red: no response at all.
Each cell is one probe run. Faded cells are incomplete probes — one leg did not answer, so the era is inconclusive.
The two probe legs separately: modern server/discover and legacy initialize.
Search UK companies, land registry prices, charities, OS locations, and traffic data
Search and retrieve listings from Kleinanzeigen, Germany's largest classifieds platform (formerly eBay Kleinanzeigen). This MCP server returns listing details including prices, descriptions, images, location, and seller information. Use it for price monitoring, market research on the German secondhand and local services market, or building lead generation tools that react to new listings. To get started, create an API key at [beatanalytics.org/kleinanzeigen](https://beatanalytics.org/kleinanzeigen) and add it to your server configuration.
Comments
Sign in to write a comment
No comments yet. Be the first.