ML Referee

io.github.scarrico由 GitHub 帳號 scarrico 發布v1.1.0更新於 Oct 29, 2026

Evaluate ML features beyond a baseline and test bounded feature repairs. Invite-only beta.

已驗證Streamable HTTP可網頁執行資料與分析AI 與機器學習

概覽

AI 產生的概覽

ML Referee 的遠端 MCP 伺服器，讓助理上傳去識別化資料集、依基準報價並執行特徵稽核，並測試有界特徵修復。

可以做什麼
  • 了解服務能力、隱私條款、支援的評估設定與就緒狀態
  • 上傳加密的去識別化資料集、活動分片或修復矩陣，並在不消耗額度的情況下預檢
  • 為稽核、修復與活動報價，接受報價後提交並追蹤稽核狀態
  • 讀取租戶私有的完成結果、簽章輸出清單與報告回執，並驗證報告雜湊
  • 記錄稽核後續情況，刪除保留的上傳或稽核
  • 查詢稽核額度餘額、兌換測試邀請或申請測試存取
適用情境
適合想讓助理判斷 ML 特徵是否優於基準，或在私有資料上診斷效果下降並測試有界特徵修復的情境，報價與額度管理也在同一連線內完成。此服務為邀請制測試版，適合已獲授權或正在申請存取的團隊。
執行需求
遠端 streamable HTTP 端點 api.mlreferee.com；未宣告本機套件或環境變數。工具涉及已驗證租戶、憑證與稽核額度，因此需要帳號與測試存取權限。資料集以去識別化的 CSV 或 JSON 內容上傳。
安裝前請注意
上傳會將資料傳送給第三方，雖然描述為加密且去識別化，仍需確認哪些資料可以離開本機環境。稽核會消耗付費稽核額度，提交稽核即預留額度。相關工具可刪除保留的上傳與稽核結果。測試邀請由營運方發放，並於 2027 年 1 月 1 日到期。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 ML Referee，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.github.scarrico%2Fmlreferee/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": {
    "ml-referee": {
      "type": "http",
      "url": "https://api.mlreferee.com/mcp"
    }
  }
}

工具

26

describe_referee

Describe Referee

Discover capabilities, privacy, and the approved public catalog.

無需輸入參數。

list_verticals

List evaluation profiles

List the three supported evaluation profiles and their discovery tags.

無需輸入參數。

get_referee_readiness

Check Referee readiness

Report connection, credential, audit-credit, and submission readiness with the next action.

無需輸入參數。

get_referee_usage

Read aggregate usage

Read aggregate, privacy-preserving Referee activity and outcome evidence for the selected audience.

輸入參數window_days

get_input_schema

Get feature-audit schema

Get neutral column roles and validation defaults for a vertical.

輸入參數vertical必填

get_repair_schema

Get feature-repair schema

Get the feature-only contract for diagnosing degradation and testing bounded repairs.

無需輸入參數。

upload_private_dataset

Upload private dataset

Encrypt a de-identified CSV/JSON payload for a short tenant-private retention window.

輸入參數data必填formatretention_seconds

upload_campaign_shard

Upload campaign shard

Encrypt one of up to 64 private feature shards for a large campaign; retain for at least 4,200 seconds.

輸入參數data必填formatretention_seconds

upload_repair_matrix

Upload repair matrix

Encrypt one complete de-identified repair matrix of up to 100 MB and 1,000 diagnostic features.

輸入參數data必填formatretention_seconds

preflight_dataset

Preflight feature audit

Validate a tenant-private upload and its baseline evidence/row identity without spending a credit.

輸入參數contract必填vertical必填upload_id必填

preflight_repair

Preflight feature repair

Validate a tenant-private feature-repair matrix without spending a credit.

輸入參數contract必填upload_id必填

quote_audit

Quote feature audit

Create a contract-bound quote for one audit credit; baseline mode and evidence cannot be substituted.

輸入參數contract必填vertical必填upload_id必填idempotency_key必填

quote_repair

Quote feature repair

Preflight and quote label-based feature repair; large jobs return a measured ETA and credit requirement.

輸入參數contract必填upload_id必填idempotency_key必填

quote_campaign

Quote feature campaign

Preflight all private feature shards, time a pilot, and quote credits and ETA for up to 1,000 candidates in one corrected search family.

輸入參數shards必填vertical必填idempotency_key必填

get_credits

Read audit credits

Read beta or paid audit-credit availability and usage.

無需輸入參數。

redeem_beta_invite

Redeem beta invite

Redeem one operator-issued invite for free beta audit credits before January 1, 2027.

輸入參數invite_code必填

request_beta_access

Request beta access

Request operator-reviewed beta access without purchasing or granting credits.

輸入參數lane必填use_case必填idempotency_key必填

get_beta_request_status

Get beta request status

Read the authenticated tenant's beta-access request status.

輸入參數request_id必填

submit_audit

Submit audit

Accept a quote and atomically reserve its disclosed audit credits.

輸入參數quote_id必填idempotency_key必填

record_audit_followup

Record audit follow-up

Record whether a completed audit changed a decision or was confirmed prospectively.

輸入參數kind必填value必填audit_id必填

get_audit_status

Get audit status

Read the state of an audit owned by the authenticated tenant.

輸入參數audit_id必填

get_audit_result

Get audit result

Read a completed tenant-private result and signed output manifest.

輸入參數audit_id必填

get_audit_receipt

Get report receipt

Read a tenant-private report fingerprint retained after report expiry or deletion. Older reports may have no record. This does not retrieve report contents.

輸入參數audit_id必填

verify_audit_report

Verify report fingerprint

Compare a locally computed SHA-256 with the retained tenant-private receipt. Use the exact downloaded result JSON bytes (not the API envelope), or UTF-8 result.report text with representation report_text. Never copy the expected hash as the candidate: compute it from the supplied artifact. A digest match does not validate a summary, factual correctness, or absence of harm. No report is uploaded.

輸入參數sha256必填audit_id必填representation

delete_audit

Delete audit

Delete retained inputs and results for an audit owned by this tenant.

輸入參數audit_id必填

delete_upload

Delete upload

Delete a tenant-private upload that is no longer needed.

輸入參數upload_id必填

版本歷史

1
  1. v1.1.0最新Oct 29, 2026

評分

已滿足適用檢查項的 83%

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

    請宣告包含 README 的 GitHub 儲存庫，或在 OAuth 受保護資源後設資料中提供 resource_documentation。

  • 授權條款不適用

    託管服務按其提供方的條款使用，因此這裡不要求授權條款。此檢查項不計入百分比。