MaxMind minFraud MCP by usefulapi

io.usefulapi由 usefulapi.io 發布官方發布者v1.36.5更新於 Nov 8, 2026

MCP server for MaxMind minFraud — score transactions for fraud risk from your AI assistant.

發布方自己的服務:Ably MCP by usefulapi

已驗證Streamable HTTP可網頁執行金融安全與監控

概覽

AI 產生的概覽

託管的 MaxMind minFraud 伺服器,讓助理為交易做詐欺風險評分並回傳真實結果。

可以做什麼
  • 為交易做詐欺風險評分,回傳總分、IP 風險與處置結果
  • 取得詳細洞察:IP 地理位置、電子郵件、地址與裝置屬性及各組成風險
  • 取得最詳細評估,包含評分原因與各因子子分數
  • 向 MaxMind 回傳交易結果(例如拒付或確認詐欺)
  • 查看當月用量並管理訂閱方案
適用情境
適合在對話中讓助理審查訂單、註冊或付款的風險,並把已確認的結果回傳以改善評分。
執行需求
遠端端點 maxmind-minfraud.usefulapi.io/mcp,無需本機安裝。透過 OAuth 登入,登入頁要求填寫 MaxMind 帳戶 ID 與授權金鑰,驗證後依使用者儲存。用戶端設定只填 URL。
安裝前請注意
登入時需提供 MaxMind 帳戶 ID 與授權金鑰;不要在用戶端設定中填入它們或 Authorization 標頭。回傳工具會向 MaxMind 寫入詐欺回饋並改變其對你流量的模型,執行前應先確認。免費方案每月限 50 次呼叫;付費方案透過 Stripe 結帳連結付款,取消後當期不退款。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 MaxMind minFraud MCP by usefulapi,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式,或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南,先向你展示發布者、端點和登入方式,經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.usefulapi%2Fmaxmind-minfraud/install.md,並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前,先告訴我它的發布者、端點和登入方式,等我確認。不要把 API 金鑰寫進命令或我會提交的檔案;問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "maxmind-minfraud-by-usefulapi": {
      "type": "http",
      "url": "https://maxmind-minfraud.usefulapi.io/mcp"
    }
  }
}

README

MaxMind minFraud MCP by usefulapi

Score transactions for fraud risk with MaxMind minFraud from Claude, Cursor, or any MCP client. Hosted, no local install — connect with your MaxMind account ID + license key.

Live endpoint: https://maxmind-minfraud.usefulapi.io/mcp · Homepage: https://usefulapi.io/maxmind-minfraud

Connect

  • Claude (claude.ai, Desktop): open Customize → Connectors, click + Add → Add custom connector, and paste https://maxmind-minfraud.usefulapi.io/mcp.
  • Claude Code: claude mcp add --transport http maxmind-minfraud https://maxmind-minfraud.usefulapi.io/mcp, then run /mcp to log in.
  • VS Code: Add to VS Code.
  • Cursor and other clients: add the URL as a remote MCP server:
json
{  "mcpServers": {    "maxmind-minfraud": {      "url": "https://maxmind-minfraud.usefulapi.io/mcp"    }  }}

Add only the URL. Do not add an Authorization header or an API key to the client config: the server signs you in with OAuth, and the login page asks for your MaxMind minFraud credentials.

Step-by-step setup, where to find your credentials, and FAQ: https://usefulapi.io/maxmind-minfraud/

On first connect you'll paste your MaxMind account ID and license key. It's validated, stored per-user, and scoped to you.

Tools

ToolTypeWhat it does
minfraud_scorereadminFraud risk score
minfraud_insightsreadminFraud Insights (detailed risk)
minfraud_factorsreadminFraud Factors (risk reasons + subscores)
minfraud_report_transactionwriteReport a transaction outcome
maxmind_minfraud_usage_statusmetaUsage status (free-tier meter)
maxmind_minfraud_request_featuremetaRequest a missing feature
maxmind_minfraud_upgrademetaUpgrade to Pro or Pro+
maxmind_minfraud_cancel_subscriptionmetaCancel the Pro subscription

read tools are read-only; write tools mutate data (clients should confirm them); meta tools report usage, manage your subscription or send a feature request.

Pricing

PlanPriceLimit
Free$050 tool calls / month
Pro$9/mo or $90/yr (2 months free)Unlimited*

*Pro has a fair use limit of 10,000 tool calls a month on this server. For more, write to [email protected].

Pro covers this server only. Subscribe with maxmind_minfraud_upgrade (it returns a Stripe Checkout link). Cancel any time with maxmind_minfraud_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running maxmind_minfraud_upgrade before then undoes the cancel. Or write to [email protected].

License

MIT — see LICENSE. Documentation only; the server is hosted.

來源:servers/maxmind-minfraud/README.md,提交 4046075

工具

4

minfraud_score

minFraud risk score

Score a transaction for fraud risk. Returns the overall risk_score (0.01–99), IP risk, disposition, and remaining query funds — the lightest, cheapest assessment. Send at least device.ip_address (plus email/billing/order for a better score). API: POST /minfraud/v2.0/score.

輸入參數emaileventorderdeviceaccountbillingpaymentshippingcredit_cardcustom_inputsshopping_cart

minfraud_insights

minFraud Insights (detailed risk)

Score a transaction AND get detailed risk insights: IP geolocation, email/address/device attributes, and per-component risk on top of the risk_score. Same request body as minfraud_score. API: POST /minfraud/v2.0/insights.

輸入參數emaileventorderdeviceaccountbillingpaymentshippingcredit_cardcustom_inputsshopping_cart

minfraud_factors

minFraud Factors (risk reasons + subscores)

The most detailed assessment: everything in Insights PLUS risk_score_reasons and per-factor subscores explaining WHY the score is what it is. Same request body as minfraud_score. API: POST /minfraud/v2.0/factors.

輸入參數emaileventorderdeviceaccountbillingpaymentshippingcredit_cardcustom_inputsshopping_cart

minfraud_report_transaction

Report a transaction outcome

WRITE — submits fraud feedback to MaxMind. Report the real-world outcome of a transaction (e.g. it was a chargeback or confirmed fraud) so minFraud can improve future scoring. This mutates MaxMind's model of your traffic; it is not a read. Requires a `tag` and at least one identifier (ip_address, maxmind_id, minfraud_id, or transaction_id). API: POST /minfraud/v2.0/transactions/report (returns HTTP 204).

輸入參數tag必填notesip_addressmaxmind_idminfraud_idtransaction_idchargeback_code

版本歷史

22
  1. v1.36.5最新Nov 8, 2026
  2. v1.36.4Nov 7, 2026
  3. v1.35.3Nov 5, 2026
  4. v1.35.2Nov 5, 2026
  5. v1.35.1Nov 4, 2026
  6. v1.35.0Nov 3, 2026
  7. v1.34.1Nov 3, 2026
  8. v1.33.0Nov 1, 2026
  9. v1.31.0Oct 31, 2026
  10. v1.30.0Oct 31, 2026
  11. v1.29.2Oct 30, 2026
  12. v1.29.0Oct 30, 2026
  13. v1.24.0Oct 26, 2026
  14. v1.21.3Oct 25, 2026
  15. v1.21.0Oct 25, 2026
  16. v1.20.0Oct 24, 2026
  17. v1.17.0Oct 23, 2026
  18. v1.16.4Oct 22, 2026
  19. v1.16.3Oct 21, 2026
  20. v1.11.1Oct 9, 2026
  21. v1.10.0Oct 9, 2026
  22. v1.0.1Sep 16, 2026

評分

已滿足適用檢查項的 100%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分

其他 Usefulapi 整合