https://mcp.cardcenteringtool.com/mcp ↗
Trading card prices and grading ROI for 1.5M+ Pokémon, Magic, Yu-Gi-Oh! and sports cards. Read-only.
Midpoint Card Prices is a remote MCP server published at mcp.cardcenteringtool.com. It has been probed 8 times since 9/12/2026. It answered in 8 of them (100.0%), a near-uninterrupted record. Median response time is 358 ms, placing it among the faster endpoints. It offers a narrow, focused set of 9 tools. On the protocol side it still runs 2025-11-25 and has not moved to the newer spec.
Can an LLM agent pick the right tool here — names, descriptions and parameter clarity are assessed.
grading_roi — Description cuts off mid-sentence, omitting critical details about ROI calculation outcomes.best_cards_to_grade — Parameter 'set_slug' lacks clarification on acceptable format or examples.trending_cards — Optional 'direction' parameter does not specify allowed values (e.g., 'rising', 'falling').Risk: 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.
search_cardsUse this first when the user names a trading card and wants its value, price, or whether to grade it. Searches 1.5M+ Pokémon, Magic, Yu-Gi-Oh!, One Piece, Lorcana, sports (baseball, basketball, football, hockey, soccer, wrestling, UFC and more) and entertainment cards by name, set, number and year, returning ungraded and PSA 10 market prices in USD from real sold listings. Returns card ids for get_card_prices, grading_roi and get_price_history. Do not use for sealed product, for cards you already have an id for, or for price prediction.
querystringrequiredgamestringset_idstringlimitintegerget_card_pricesUse this when the user wants the full current value of a specific card: ungraded prices by condition (NM/LP/MP/HP) and graded prices for every company and grade on record (PSA, CGC, BGS, SGC, TAG). Requires a card id from search_cards. Prices are USD market values from real sold listings, refreshed daily. Do not use to search by name.
card_idstringrequiredgrading_roiUse this when the user asks whether a card is worth grading, submitting to PSA/CGC/BGS/SGC/TAG, or what a PSA 10 adds. Returns raw vs PSA 9 vs PSA 10 market prices, the gem premium, net profit after grading fees per outcome, expected value by gem probability, the break-even gem rate, which company pays most, and a plain-language verdict. Requires a card id from search_cards. It does not assess the condition of the user's copy.
card_idstringrequiredgrading_fee_usdnumberget_price_historyUse this when the user asks how a card's price has changed over weeks or months, or wants a trend for the raw or a PSA-graded series. Returns dated USD market values for the last 7 to 180 days. Requires a card id from search_cards. Do not use for forecasts.
card_idstringrequireddaysintegergradestringbest_cards_to_gradeUse this when the user asks which cards in a game, sport or set have the biggest payoff from grading. Ranks priced cards by expected net profit at a 50% gem rate (half PSA 10, half PSA 9, minus raw and the fee), requiring both PSA 9 and PSA 10 prices so thin-market outliers are excluded. Returns card ids for grading_roi. Do not use for a single named card.
gamestringrequiredset_slugstringgrading_fee_usdnumberlimitintegertrending_cardsUse this when the user asks which cards are rising, hot, spiking, crashing or trending, in one game or across all games. Returns the biggest 30-day gainers (or drops) with the percentage change, measured on the PSA 10 price where the card has one and on the raw price otherwise; moves over 300% are excluded as bad data. Do not use for a single named card or for long-term history.
gamestringdirectionstringmin_market_usdnumberlimitintegerliquid_moversUse this when the user wants cards that are both rising in price and easy to sell: recent gainers filtered to cards with at least 25 recorded sales a year and a raw price of at least $5, across all games and sports. Better than trending_cards for flipping or selling decisions. Do not use for a single named card.
gamestringlimitintegerlist_setsUse this to find the set id for a game or sport (e.g. "Evolving Skies", "2019 Panini Prizm") before calling get_set_cards, or when the user asks which sets exist. Newest first. Do not use to price a single card.
gamestringrequiredquerystringlimitintegerget_set_cardsUse this when the user wants the most valuable cards in a specific set or a priced checklist of a set. Requires a set id from list_sets. Returns raw and PSA 10 USD prices per card. Do not use for a single named card; use search_cards instead.
gamestringrequiredset_idstringrequiredsortstringlimitintegerDerived 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-cardcenteringtool-card-prices)<a href="https://mcpmetrics.io/servers/com-cardcenteringtool-card-prices"><img src="https://mcpmetrics.io/badge/com.cardcenteringtool/card-prices/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.
Public read-only MCP server for HODLXXI agent identity, trust, receipts, and verification.
Real sold prices, history & PSA population for graded Pokémon cards (EN/JP/CN). Knows nicknames.
Read-only MCP for Rialto quotes and swap preflight on Robinhood Chain. No signing or broadcast.
Neutral prices + PSA population for PSA-graded vintage Pokémon (WotC 1999–2003). Read-only.
Public record of one read only walk over the official MCP registry: who answered, tools, who pays.
Trades, stats, playbooks and notes from your Trandence trading journal. Read-only by default.
| Run | Era | Modern | ms | Legacy | ms | Versions |
|---|---|---|---|---|---|---|
| 2026-09-13 06:40:42 | Legacy | 400 | 378 | 200 | 366 | 2025-11-25 |
| 2026-09-13 04:35:29 | Legacy | 400 | 362 | 200 | 358 | 2025-11-25 |
| 2026-09-13 01:33:33 | Legacy | 400 | 241 | 200 | 226 | 2025-11-25 |
| 2026-09-12 23:31:36 | Legacy | 400 | 366 | 200 | 372 | 2025-11-25 |
| 2026-09-12 21:29:15 | Legacy | 400 | 271 | 200 | 290 | 2025-11-25 |
| 2026-09-12 19:27:29 | Legacy | 400 | 293 | 200 | 299 | 2025-11-25 |
| 2026-09-12 17:24:09 | Legacy | 400 | 380 | 200 | 398 | 2025-11-25 |
| 2026-09-12 15:21:42 | Legacy | 400 | 224 | 200 | 219 | 2025-11-25 |
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.
Comments
Sign in to write a comment
No comments yet. Be the first.