WHP Standing

io.github.wheelerhubbell由 GitHub 帳號 wheelerhubbell 發布v1.0.5更新於 Nov 7, 2026

Paid, signed evaluations of structured claims and supporting sources. MCP; x402 on Base.

已驗證Streamable HTTP可網頁執行金融安全與監控AI 與機器學習

概覽

AI 產生的概覽

遠端 MCP 伺服器,依 Decision Integrity Protocol 評估結構化主張,回傳 Ed25519 簽章的 standing 判定,每次呼叫透過 Base 上的 x402 以 USDC 付費。

可以做什麼
  • 查詢 standing 合約、設定、schema 與授權前提
  • 依 Decision Integrity Protocol 評估命題並取得簽章判定
  • 帶上付款簽章重試以完成 1 USDC Base 付款挑戰
  • 憑買方驗證取回原始簽章標記或否定評估內容,且不再收費
適用情境
適合需要在跨越會改變狀態的邊界前,對某項主張或操作是否具備可追溯授權與來源取得機器可驗證簽章結論的代理或流程。當可稽核的第三方判定值得按次付費時使用。
執行需求
需要遠端 streamable HTTP 端點;未宣告本機套件或環境變數。付費呼叫需要已儲值的 Base 錢包,以及支援 USDC 付款簽章的 x402 用戶端;README 指出端對端流程尚未對線上服務驗證。
安裝前請注意
每次評估在 Base 上花費 1 USDC 並需提供付款簽章;伺服器聲明其從不持有錢包金鑰或授予支出權限,簽章由買方自行完成。付費不保證正面結果,評估失敗不會產生標記。README 範例使用私鑰環境變數,請勿將錢包金鑰放入共用設定。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 WHP Standing,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.wheelerhubbell%2Fwhp-standing/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": {
    "whp-standing": {
      "type": "http",
      "url": "https://api.wheelerhubbellpublishing.com/mcp"
    }
  }
}

README

@wheelerhubbell/whp-standing-client

Fail-closed epistemic standing middleware for autonomous AI agents.
Governed by the Authority Conservation Principle: $A(c) \le P(c)$ (Authority cannot exceed provenance).

Standing detects and stops Coherent Substitution—when an AI agent silently replaces the assigned task with an adjacent one ($q \to q^*$), reasons coherently about the replacement, and executes unauthorized state mutations.


📚 Case Studies & Theory

  • Coherent Substitution (v1.1): Theoretical formulation of proposition integrity and why systems fail before their reasoning becomes wrong.
  • Mata v. Avianca Epistemic Autopsy: Controlled forensic breakdown showing how an agent citing 100% verified sources still fails by answering the wrong question ($Q_0 \to Q_1$).

⚡ 1-Line Middleware Integration

Install the package:

bash
npm install @wheelerhubbell/whp-standing-client

Place guardAction immediately before tool execution:

javascript
import { guardAction } from '@wheelerhubbell/whp-standing-client';
// Before any agent tool runs:await guardAction(toolCall, {  standing: executionContext.standing});
// Proceed only if standing is warrantedreturn await tool.execute(toolCall.arguments);

If an agent attempts a state-changing operation (file deletion, database write, API mutation) without attributable upstream authorization or provenance, guardAction throws a StandingViolationError before the boundary is crossed.


🔍 Observability: evaluateStanding

For inspection without throwing:

javascript
import { evaluateStanding } from '@wheelerhubbell/whp-standing-client';
const decision = await evaluateStanding(toolCall, context);if (!decision.allowed) {  console.warn(`Blocked [${decision.code}]: ${decision.message}`);  return decision;}

Diagnostic Decision Object

json
{  "allowed": false,  "code": "MISSING_UPSTREAM_PROVENANCE",  "actionId": "call_8cb2f1",  "toolName": "delete_database_table",  "required": ["authority", "provenance"],  "observed": {    "toolName": "delete_database_table",    "arguments": { "table": "users" },    "missing": ["provenance", "authority"]  },  "message": "Tool execution blocked for 'delete_database_table': no attributable upstream authorization or provenance."}

🛡️ Core Semantics

  • Fail-Closed by Default: Any state-changing action missing valid provenance or authority is rejected.
  • Authority Windows: Bounded by valid_until timestamps.
  • Loop & Recursion Bounds: Halts unbounded agent loops (executionCount > maxExecutionCount).
  • Zero Overhead for Reads: Passive read operations execute without blocking.

🌐 Verifiable Network Verification

The live service has a plain front door for ordinary x402 agents: POST /v1/evaluate with subject, claim and optional provenance, priced at 1.00 USDC on Base (x402 v2). It returns a signed evaluation record. That record is not a sealed Standing Mark. Marks are issued through POST /v1/evaluations, which takes signed submissions per the published contract.

Example using the official x402 client (requires your own funded wallet and spending limits; not yet verified end to end against the live service):

javascript
import { x402Client, wrapFetchWithPayment } from '@x402/fetch';import { registerExactEvmScheme } from '@x402/evm/exact/client';import { privateKeyToAccount } from 'viem/accounts';
const client = new x402Client();registerExactEvmScheme(client, { signer: privateKeyToAccount(process.env.EVM_PRIVATE_KEY) });const fetchWithPayment = wrapFetchWithPayment(fetch, client);
const res = await fetchWithPayment('https://api.wheelerhubbellpublishing.com/v1/evaluate', {  method: 'POST',  headers: { 'Content-Type': 'application/json' },  body: JSON.stringify({    subject: 'agent-session-42',    claim: 'Agent executed system mutation',    provenance: { source: 'user-intent', authority: 'admin' }  })});console.log(await res.json());

Direct Autonomous Client (StandingClient)

The client provides built-in autonomous wallet signing and settlement over Base USDC (x402-v2):

javascript
import { StandingClient } from '@wheelerhubbell/whp-standing-client';
const client = new StandingClient({ privateKey: process.env.BASE_WALLET_KEY });
// Front-door structural evaluation (POST /v1/evaluate)const record = await client.evaluate({  subject: 'Production Deployment',  claim: 'Deploy release to production',  provenance: { source: 'ci/cd pipeline', authority: 'release-engineering' }});console.log('Outcome:', record.evaluation?.determination?.outcome);console.log('Record Hash:', record.record_hash);
// Or purchase an authoritative sealed Standing Mark (POST /v1/evaluations):// const mark = await client.purchase(signedSubmission);

License

MIT © Wheeler Hubbell Publishing

來源:packages/client/README.md,提交 ffb444e

工具

4

whp_evaluate

Evaluate a proposition under Decision Integrity Protocol and receive an Ed25519-signed Standing determination. Calling without payment returns the exact 1 USDC Base payment challenge. Pass payment_signature to settle and receive the signed determination.

輸入參數claim必填api_keysubjectprovenanceidempotency_keypayment_signature

whp_standing_contract

Discover WHP Standing: Machine-verifiable standing under explicit authority and bounds. Includes exact profile, schema, authority prerequisites and owner-authorized payment contract.

無需輸入參數。

whp_standing_evaluation

Request a WHP Standing Evaluation. First call returns the exact HTTP 402 payment terms. Supply only the buyer’s own pre-authorized payment signature on retry. Paying does not establish standing; a failed assessment has no Mark.

輸入參數client_proofsubmission_raw必填payment_signature

whp_standing_result

Retrieve the exact original WHP Standing Mark or negative assessment bytes with buyer authentication, without another charge.

輸入參數purchase_id必填client_proof必填

版本歷史

5
  1. v1.0.5最新Oct 31, 2026
  2. v1.0.4Oct 8, 2026
  3. v1.0.2Oct 5, 2026
  4. v1.0.1Sep 23, 2026
  5. v1.0.0Sep 16, 2026

評分

已滿足適用檢查項的 90%

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

    請在儲存庫或註冊中心條目中宣告授權條款。