# Midpoint Card Prices (remote · mcp.cardcenteringtool.com)

Trading card prices and grading ROI for 1.5M+ Pokémon, Magic, Yu-Gi-Oh! and sports cards. Read-only.

- Trust score: 76/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-25

## Components

- remote · `mcp.cardcenteringtool.com`: 76/100 (this document), [markdown](https://verifymcp.io/servers/com-cardcenteringtool-card-prices/mcp.md), [page](https://verifymcp.io/servers/com-cardcenteringtool-card-prices/mcp)

## Channel facts

- Endpoint: `https://mcp.cardcenteringtool.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-25.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 70/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1439 tokens (~159/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 47/100
  - Stability observed for 14 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 91/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 68% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Midpoint Card Prices MCP server?

Midpoint Card Prices is a hosted endpoint at https://mcp.cardcenteringtool.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-cardcenteringtool-card-prices 'https://mcp.cardcenteringtool.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-cardcenteringtool-card-prices": {
      "url": "https://mcp.cardcenteringtool.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-cardcenteringtool-card-prices": {
      "type": "http",
      "url": "https://mcp.cardcenteringtool.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-cardcenteringtool-card-prices]
url = "https://mcp.cardcenteringtool.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-cardcenteringtool-card-prices": {
      "type": "remote",
      "url": "https://mcp.cardcenteringtool.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-cardcenteringtool-card-prices --url 'https://mcp.cardcenteringtool.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-cardcenteringtool-card-prices:
    url: "https://mcp.cardcenteringtool.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-cardcenteringtool-card-prices": {
      "Transport": "http",
      "Url": "https://mcp.cardcenteringtool.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-cardcenteringtool-card-prices -t streamable-http -u 'https://mcp.cardcenteringtool.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-cardcenteringtool-card-prices": {
      "type": "http",
      "url": "https://mcp.cardcenteringtool.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-25 (score 76, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-24 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-22 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-20 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-19 (score 73, 0)

- [cosmetic] “liquid_movers” added an optional parameter “include_unknown_volume”

### 2026-09-17 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (9)

### `search_cards` (~229 tokens)

Search card prices

Use 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.

Input parameters:

- `game` (string): Restrict to one game or sport. Omit when unsure.
- `limit` (integer)
- `query` (string, required): Card name, optionally with set, number or year. Examples: "Umbreon VMAX Evolving Skies", "1986 Fleer Jordan", "Charizard base set 4/102".
- `set_id` (string): Expansion id from list_sets, to search inside one set.

Output parameters:

- `cards` (array)
- `count` (integer)
- `matched_on` (string): The search term that produced the results
- `note` (string)
- `query` (string)

### `get_card_prices` (~126 tokens)

Get card price ladder

Use 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.

Input parameters:

- `card_id` (string, required): Catalog card id from search_cards, e.g. "swsh7-215" or "pricecharting-1821843".

Output parameters:

- `captured_on` (string|null): Date of the latest price capture (UTC)
- `card` (object)
- `currency` (string)
- `graded` (array)
- `links` (object)
- `other_variants` (array): Other printings of the same card id (reverse holo, 1st edition…) with their own prices. Never mix these with the main ladder.
- `raw` (array)
- `raw_note` (string|null): Set when the raw condition ladder is out of order (thin data): treat raw prices as low confidence.
- `summary` (object)
- `variant` (string|null): The printing the raw and graded rungs refer to (e.g. "holofoil", "1st edition"). Other printings are listed under other_variants.

### `grading_roi` (~157 tokens)

Is this card worth grading?

Use 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.

Input parameters:

- `card_id` (string, required): Catalog card id from search_cards.
- `grading_fee_usd` (number): Grading fee to assume. Defaults to a $25 economy tier; the table also shows $50 and $150.

Output parameters:

- `assumed_fee_usd` (number)
- `break_even_gem_probability` (number|null): Chance of a PSA 10 needed to break even at the assumed fee; null when grading never breaks even
- `captured_on` (string|null)
- `card` (object)
- `currency` (string)
- `expected_value` (array)
- `gem_premium_multiple` (number|null): PSA 10 price ÷ raw price
- `links` (object)
- `net_after_fee` (array)
- `psa10_usd` (number|null)
- `psa9_usd` (number|null)
- `raw_market_usd` (number|null)
- `top_grade_by_company` (array)
- `verdict`

### `get_price_history` (~125 tokens)

Get price history

Use 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.

Input parameters:

- `card_id` (string, required): Catalog card id from search_cards.
- `days` (integer)
- `grade` (string): PSA grade for a graded series, e.g. "10" or "9". Omit for the raw (ungraded) series.

Output parameters:

- `card_id` (string)
- `change_note` (string|null): Set when one step between consecutive captures accounts for the change: usually a data correction, not a market move. change_pct is null in that case.
- `change_pct` (number|null): First-to-last change; null when change_note is set because a single step carries it.
- `coverage` (object): How many of the requested days have a capture, and how to read repeated or sparse values.
- `currency` (string)
- `days` (integer)
- `first_usd` (number|null)
- `last_usd` (number|null)
- `links` (object)
- `name` (string)
- `points` (array): Oldest first. Graded series only contain days with sales; gaps are normal.
- `series` (string): "raw" or "PSA <grade>"
- `source` (string)
- `variant` (string|null): The printing the series follows (e.g. "holofoil"); other printings are separate markets and are never mixed in.

### `best_cards_to_grade` (~164 tokens)

Best cards to grade

Use 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.

Input parameters:

- `game` (string, required): Game or sport to rank.
- `grading_fee_usd` (number): Grading fee to assume. Defaults to $25.
- `limit` (integer)
- `set_slug` (string): Optional set slug (as used on /sets/<game>/<slug>) to rank inside one set.

Output parameters:

- `assumed_fee_usd` (number)
- `cards` (array)
- `count` (integer)
- `criteria` (string)
- `game` (string)
- `links` (object)

### `trending_cards` (~161 tokens)

Trending cards (30-day price movers)

Use 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.

Input parameters:

- `direction` (string): "up" = biggest gainers, "down" = biggest drops.
- `game` (string): Restrict to one game or sport; omit for all.
- `limit` (integer)
- `min_market_usd` (number): Ignore cards whose raw price is below this.

Output parameters:

- `cards` (array)
- `count` (integer)
- `criteria` (string)
- `direction` (string)
- `excluded_unstable` (integer): Candidates dropped because their own 40-day series did not hold together (too few captures, a baseline that swings >2×, a >6× range, or a one-capture jump).
- `game` (string|null)
- `window_days` (number)

### `liquid_movers` (~143 tokens)

Liquid movers (rising cards that actually sell)

Use 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.

Input parameters:

- `game` (string): Restrict to one game or sport; omit for all.
- `include_unknown_volume` (boolean): Also include cards whose yearly sales count is not tracked (mostly Pokémon from the Scrydex source). Off by default so every result has a verifiable sales figure.
- `limit` (integer)

Output parameters:

- `as_of` (string): When this ranking was computed (ISO 8601)
- `cards` (array)
- `count` (integer)
- `criteria` (string)
- `excluded_unstable` (integer): Candidates dropped because their own 40-day raw series did not hold together.
- `volume_verified` (boolean): False when the list had to include cards whose yearly sales count is not tracked (Pokémon and other Scrydex-sourced games have no volume data).

### `list_sets` (~107 tokens)

List sets / expansions

Use 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.

Input parameters:

- `game` (string, required)
- `limit` (integer)
- `query` (string): Optional substring to filter set names, e.g. "evolving" or "2019 prizm".

Output parameters:

- `count` (integer)
- `game` (string)
- `links` (object)
- `sets` (array)

### `get_set_cards` (~112 tokens)

Cards in a set with prices

Use 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.

Input parameters:

- `game` (string, required)
- `limit` (integer)
- `set_id` (string, required): Expansion id from list_sets.
- `sort` (string): "value" = most valuable first; "number" = checklist order.

Output parameters:

- `cards` (array)
- `count` (integer)
- `game` (string)
- `set_id` (string)
- `set_name` (string|null)
- `total_cards` (integer)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-cardcenteringtool-card-prices/mcp#diagnostics

## Score history

- 2026-09-25: 76
- 2026-09-24: 76
- 2026-09-23: 75
- 2026-09-22: 75
- 2026-09-21: 74
- 2026-09-20: 74
- 2026-09-19: 73
- 2026-09-18: 73
- 2026-09-17: 73
- 2026-09-16: 72
- 2026-09-15: 72
- 2026-09-14: 71
- 2026-09-13: 71
- 2026-09-12: 70
- 2026-09-11: 70

## Common questions

### What is the Midpoint Card Prices MCP server?

Midpoint Card Prices is an MCP server listed in the public MCP registry as com.cardcenteringtool/card-prices. Trading card prices and grading ROI for 1.5M+ Pokémon, Magic, Yu-Gi-Oh! and sports cards. Read-only. This page covers its hosted endpoint (https://mcp.cardcenteringtool.com/mcp).

### Is the Midpoint Card Prices MCP server safe to use?

Midpoint Card Prices scores 76 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Midpoint Card Prices MCP server expose?

Midpoint Card Prices exposes 9 tools: search_cards, get_card_prices, grading_roi, get_price_history, best_cards_to_grade, and 4 more. Their descriptions and schemas cost roughly 1,324 tokens of context every time the server is loaded.

### Does the Midpoint Card Prices MCP server require authentication?

No. We connected to Midpoint Card Prices without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Midpoint Card Prices MCP server still maintained?

Midpoint Card Prices is still listed as active in the MCP registry. We last reached this channel on 25 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://mcp.cardcenteringtool.com/mcp
- Repository: https://github.com/kolourr/midpoint-mcp
- Website: https://www.cardcenteringtool.com/mcp
- Changelog RSS feed: https://verifymcp.io/servers/com-cardcenteringtool-card-prices/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-cardcenteringtool-card-prices/mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-cardcenteringtool-card-prices/mcp