Argus Console — AI Agent Test Lab

io.github.igor-vii由 GitHub 帳號 igor-vii 發布v0.1.2更新於 Nov 5, 2026

Adversarial testing for AI agents that move money: engine battery, Ed25519-sealed verdict reports.

發布方自己的服務：Argus: Belgian tender insights

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

Argus Console 讓助理驗證代理端點、對涉及金流的 AI 代理執行免費模擬或付費的真實對抗測試，並取得判定報告。

可以做什麼
  • 驗證與列出代理：透過 well-known 路徑上的驗證權杖確認端點歸屬，並列出已註冊代理及其免費模擬額度。
  • 執行免費 MOCK 模擬：以確定性模擬跑完整流程（資金守門閘與故障探針），不會請求代理端點。
  • 執行真實引擎測試：使用付費額度對線上用戶端代理執行標準與故障情境，回傳執行 ID。
  • 取得執行報告：讀取資金守門結果、判定計數、逐探針判定，以及已證實、違規、未確立清單。
適用情境
適合正在開發或審查會支出、收款或結算資金的 AI 代理，並希望取得對抗性檢查與有證據支撐的判定。可先跑免費模擬了解流程表現，再決定是否消耗付費額度進行真實執行。
執行需求
遠端 streamable HTTP 端點 console.argus-lab.tech；未宣告套件、環境變數或標頭。代理需先註冊，並在端點 well-known 路徑提供驗證權杖。真實引擎執行會消耗付費額度，且僅適用於用戶端代理。
安裝前請注意
真實引擎執行會消耗付費額度並作用於線上代理端點；不支援 x402 的代理會在資金守門閘失敗並自動退款。執行可能耗時數分鐘。驗證需在端點上公開權杖檔案。免費模擬每 24 小時限 25 次。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Argus Console — AI Agent Test Lab，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.igor-vii%2Fargus-console/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": {
    "argus-console-ai-agent-test-lab": {
      "type": "http",
      "url": "https://console.argus-lab.tech/mcp"
    }
  }
}

README

Argus Agent Test Lab — public proof layer

[latest-seal] [site-build]

Adversarial testing for AI agents that move money · argus-lab.tech

The lab breaks AI agents that spend, receive and settle money — buyer and merchant agents, and the SDKs, protocols and rails that sign and settle on their behalf — then seals every verdict in a public, hash-chained registry.

This repository is the public proof layer of Argus: the sealed, hash-chained evidence registry, the verification tooling, and the source of argus-lab.tech. It exists so that every public claim the lab makes can be checked by anyone, without trusting anyone:

bash
git clone https://github.com/igor-vii/Argus-Agent-Test-Labcd Argus-Agent-Test-Labnode tools/registry/verify-registry.mjs# → registry intact: N records, chain head …

Verification uses only the Node.js standard library — no npm install, no network access, no trust in this README.

What is sealed here

Records in attestations/records/ are Ed25519-signed and hash-chained (prev_record_hash → chain head). Each record pins the sha256 of its evidence files. A seal attests run validity and findings completeness — never bug-freeness.

Repository boundary (record 0013)

As of sealed record #0013, the product layer — the testing engine, scenario library, SUT harnesses, rail adapters and engagement archives — is developed in a private repository. The public repository retains the proof layer only. The exact moment of the split and the last public snapshot are themselves sealed and hash-pinned:

The split is forward-only: no history rewrite, no force-push. Versions up to the snapshot commit remain public history, and everything referenced from public threads (e.g. docs/block-b/fixtures/S-BS-06/ on branch block-b/v1-scenarios, referenced from x402 issue #3866) stays public and byte-identical. Sealed evidence paths pinned by records #0000–#0012 are permanent and were retained.

Repository layout

attestations/        signed, hash-chained records + public key + indextools/registry/      sign / verify tooling (node stdlib only)tools/paypal-adapter/evidence/   sealed live-run evidence (records 0001–0002)site/                argus-lab.tech source (Next.js; prebuild re-verifies the registry)docs/block-b/        sealed fixtures and evidence (S-BS series, records 0003+)docs/inngest-battery/  sealed evidence + repro harness (record 0005)docs/t1-mcp-tool-idempotency/  sealed external verification (record 0009)sut-x402-pr3920/     sealed SUT evidence, x402 PR #3920 cycles (records 0008, 0012)src/tests/blockb/SBS19_BlockRunNano.test.ts   sealed evidence (record 0006).github/             CI: verify registry → OG cover → IndexNow → Vercel deploy

About Argus

Argus is an independent black-box testing laboratory for AI agents and agent-based payment systems. It runs controlled failure scenarios against observable systems under test (SUTs), captures evidence at protocol boundaries, evaluates explicit assertions, and produces evidence-backed verdicts — the public ones are the sealed records above.

Agent → Scenario → SUT → Evidence → Verdict

  • Sealed case work: x402 (#3866, PR #3920), Inngest (#5091), BlockRun (blockrun-nano-client #18), Nevermined, mcp-tool-idempotency
  • Commercial engagements (scenario conformance runs, release verification): argus-lab.tech

Argus lives in a repository separate from the systems it tests and interacts with SUTs through defined external interfaces and observable behavior only.

Status

Public case studies and production-capability claims are added only when supported by verified run evidence — the registry is the source of truth, not this README.

來源：README.md，提交 db48768

工具

5

argus_verify_agent

Verify ownership of an agent endpoint: checks that the verify token is served at https://<endpoint>/.well-known/argus-verify.txt. Run this before registering the agent in Argus Console.

輸入參數token必填endpoint必填

argus_list_agents

List the user's registered agents (name, role, endpoint) and their free tier. MOCK simulation is FREE: no payment, nothing to deploy, rolling cap 25 runs / 24h (paid quota untouched). The response includes freeSimulation { used, limit, resetsAt }.

無需輸入參數。

argus_run_simulation

Run a free MOCK battery against a registered agent: the full pipeline (money guard gate + fault probes) as a deterministic simulation seeded by the endpoint. Simulation only — this is a stand demo, no request reaches the agent endpoint. Does not touch paid quota; rolling cap 25 runs / 24h. Waits for completion and returns the report.

輸入參數agent必填battery

argus_run_engine

Run the REAL Argus engine battery (canonical S8 + fault scenarios) against a live agent using paid quota. CLIENT agents only. Agents that do not speak x402 fail the money-guard gate and the run is auto-refunded (net 0). May take minutes — returns the run id to poll via argus_get_run_report.

輸入參數agent必填battery

argus_get_run_report

Fetch the report of a finished run: money guard outcome, verdict counts, per-probe verdicts, proven/violations/not-established lists.

輸入參數run_id必填

版本歷史

2
  1. v0.1.2最新Nov 5, 2026
  2. v0.1.1Nov 5, 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。

其他 Argus 整合

Argus: Belgian tender insights

ing.argus官方發布者

讓助理取得比利時公共招標資訊，包括投標方、得標方、得標價格以及授標報告評分。

Streamable HTTP可網頁執行驗證方式
商業與電商需要憑證Oct 24, 2026

Argus

由 GitHub 帳號 r0ptik 發布

Argus 可附加到執行中的 Windows 行程，為 AI 助理提供執行期逆向工程證據：記憶體位元組、反組譯、匯入解析、呼叫鏈與假設帳本。

STDIO僅桌面
開發者工具尚未驗證Oct 24, 2026

Argus

由 GitHub 帳號 pochtmanr 發布

讓助理透過本機 API 操作 Argus 反偵測瀏覽器設定檔，每個設定檔都有自己的指紋、代理與 Cookie 儲存區。

STDIO僅桌面
瀏覽器自動化尚未驗證Oct 24, 2026

Argus

由 GitHub 帳號 ironclawdevs27 發布

Argus 透過 MCP 在 Chrome 中對本機執行中的應用程式做自動化 Web QA，並把依嚴重度排序的問題報告回傳給 AI 助理。

STDIO僅桌面
瀏覽器自動化尚未驗證Oct 24, 2026

Argus Decision Mcp

由 GitHub 帳號 commet 發布

本機優先的決策帳本，讓助理記錄你的決定、可證偽的預測與確認日期，並在現實能回答時把它們帶回來。

STDIO僅桌面
效率與工作流6 個工具Oct 29, 2026