# io.github.cdkbotmcp/cdk-mcp (remote · mcp.cdk.bot)

Buy game keys, gift cards, and subscriptions via x402 USDC on Base. 8 MCP tools, no install.

- Trust score: 62/100 (medium)
- Change this week: +1
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.cdk.bot`: 62/100 (this document), [markdown](https://verifymcp.io/servers/cdkbotmcp-cdk-mcp/mcp.md), [page](https://verifymcp.io/servers/cdkbotmcp-cdk-mcp/mcp)

## Channel facts

- Endpoint: `https://mcp.cdk.bot/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 2026-08-03.

- **Endpoint Security**: 46/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 8 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS not yet verified: we couldn't determine whether a plaintext access path exists.
  - 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**: 75/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 926 tokens (~115/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http cdkbotmcp-cdk-mcp https://mcp.cdk.bot/mcp
```

### Codex

```toml
[mcp_servers.cdkbotmcp-cdk-mcp]
url = "https://mcp.cdk.bot/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "cdkbotmcp-cdk-mcp": {
      "type": "remote",
      "url": "https://mcp.cdk.bot/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add cdkbotmcp-cdk-mcp --url https://mcp.cdk.bot/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  cdkbotmcp-cdk-mcp:
    url: "https://mcp.cdk.bot/mcp"
```

### Other

```json
{
  "mcpServers": {
    "cdkbotmcp-cdk-mcp": {
      "type": "http",
      "url": "https://mcp.cdk.bot/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.

### 2026-08-02 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 61, −2)

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

### 2026-07-30 (score 63, +1)

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

### 2026-07-28 (score 62, +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.

### 2026-07-27 (score 61, +1)

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

### 2026-07-26 (score 60)

First indexed and scored.

## MCP tools (8)

### `search_games` (~177 tokens)

CDK Bot: search the catalog of digital products (game keys, gift cards, DLC) by title, platform, device, region, or language. Returns a best match with alternatives (smart matching). Use browse_filters first to see valid filter values.

Input parameters:

- `device` (string): Target device filter (e.g. PC, PS5, Xbox Series X|S)
- `language` (string): Language filter (ISO 639-1 code like "en", "pl", or "multilanguage")
- `platform` (string): Platform/storefront filter (e.g. Steam, PSN, Xbox Live)
- `query` (string, required): Game title or search keywords (e.g. "GTA V", "Elden Ring")
- `region` (string): Region filter (e.g. WORLDWIDE, EUROPE)

### `get_game_details` (~65 tokens)

CDK Bot: get detailed information about a specific digital product (game key, gift card, DLC) including price, activation instructions, and delivery time. Use the game_id from search_games results.

Input parameters:

- `game_id` (string, required): Game ID (UUID) from search results

### `browse_filters` (~40 tokens)

CDK Bot: list all available platforms, devices, regions, and languages for filtering digital product searches. Call this first to know what filter values are valid.

### `get_price_quote` (~91 tokens)

CDK Bot: lock the current price for a digital product and get USDC payment instructions. Returns a quote_id valid for 5 minutes. After paying, use confirm_purchase with the tx_hash and quote_id.

Input parameters:

- `chain` (string): Payment chain. Use "base-sepolia" for sandbox testing with mock keys.
- `game_id` (string, required): Game ID to get a price quote for

### `confirm_purchase` (~228 tokens)

CDK Bot: receive the product key after paying. Two ways to pay: (1) one-shot — pass x_payment, a signed EIP-3009 "exact" X-PAYMENT header (from accepts[] in get_price_quote); the facilitator settles it gaslessly, no tx_hash needed. (2) two-step — send USDC yourself, then pass tx_hash + quote_id.

Input parameters:

- `chain` (string): Payment chain (default: "base")
- `game_id` (string, required): Game ID being purchased
- `quote_id` (string): Required WITH tx_hash — locks the quoted price and prevents front-running. Not needed with x_payment.
- `tx_hash` (string): Two-step flow: the USDC payment transaction hash on Base. Provide this OR x_payment.
- `x_payment` (string): One-shot flow: a base64-encoded EIP-3009 "exact" X-PAYMENT payload signed by the buyer wallet for accepts[0] from get_price_quote. Settles gaslessly via the facilitator — no tx_hash/quote_id needed.

### `check_order` (~73 tokens)

CDK Bot: check the status of a purchase order. Provide wallet_address to retrieve the product key. Pending orders are automatically polled for fulfillment.

Input parameters:

- `order_id` (string, required): Order ID (UUID) from a previous purchase
- `wallet_address` (string): Buyer wallet address. Required to retrieve the product key.

### `request_refund` (~127 tokens)

CDK Bot: submit a refund claim for a purchased product key. Must be within 30 days of purchase. Delivery failures (not_delivered) are auto-approved instantly. Key issues are verified within 24 hours.

Input parameters:

- `order_id` (string, required): Order ID to refund
- `reason` (string, required): Reason: key_invalid (activation error), key_already_redeemed (used before delivery), wrong_product (wrong platform/region/edition), not_delivered (payment confirmed but no key received)
- `wallet_address` (string, required): Buyer wallet address (must match the order)

### `submit_review` (~125 tokens)

CDK Bot: rate a completed purchase (1-5 stars). Helps improve the service. One review per order. Requires order_id and the wallet_address used for payment.

Input parameters:

- `agent_name` (string): Your agent/client name (e.g. "Claude Desktop", "Cursor")
- `comment` (string): Optional comment about the purchase experience
- `order_id` (string, required): Order ID to review
- `rating` (integer, required): Rating from 1 (poor) to 5 (excellent)
- `wallet_address` (string, required): Buyer wallet address (must match the order)

## Diagnostics

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

## Score history

- 2026-08-03: 62
- 2026-08-02: 62
- 2026-08-01: 61
- 2026-07-31: 61
- 2026-07-30: 63
- 2026-07-29: 62
- 2026-07-28: 62
- 2026-07-27: 61
- 2026-07-26: 60

## Links

- Remote endpoint: https://mcp.cdk.bot/mcp
- Repository: https://github.com/cdkbotmcp/cdk-mcp
- Website: https://cdk.bot/
- Changelog RSS feed: https://verifymcp.io/servers/cdkbotmcp-cdk-mcp/mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/cdkbotmcp-cdk-mcp/mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/cdkbotmcp-cdk-mcp/mcp