Imperium Workflow Studio — Multi-Agent DAG & Pipeline Executor

dev.agentdiet由 agentdiet.dev 發布官方發布者v7.0.17更新於 Oct 26, 2026

Execute multi-step A2A & MCP agent workflows with atomic x402/MPP settlement.

發布方自己的服務:AgentDiet AI Token Diet & Context Window Distiller

已驗證Streamable HTTP可網頁執行效率與工作流商業與電商AI 與機器學習

概覽

AI 產生的概覽

遠端 MCP 伺服器,讓助理搜尋付費工具市集、執行單一工具或四工具組合,並查看預付代理錢包餘額。

可以做什麼
  • 依能力關鍵字搜尋已索引的 MCP 與 HTTP 402 工具市集,回傳含價格、信任分數與 SLA 等級的排序端點
  • 依 slug 執行單一原生工具,或代理呼叫外部市集工具 URL,按次計費
  • 一次呼叫平行執行四工具原生工作流程組合,回傳統一檔案
  • 查看代理帳戶帳本:剩餘免費試用次數、預付美元餘額、累計支出、API 呼叫數與節省的 token 數
適用情境
適合需要探索並付費使用第三方工具,或對代幣、公司網域、程式碼倉庫、研究主題做多來源盡職調查而不想多輪往返的情境。批次付費執行前先查餘額。
執行需求
需要遠端 streamable HTTP 端點;未宣告任何套件、環境變數或標頭。付費執行需要預付美元餘額或免費試用次數,工具說明提到可透過 Stripe 或 USDC 儲值。
安裝前請注意
執行工具會實際花錢:單次呼叫約 0.001 至 0.02 美元,組合約 0.015 至 0.03 美元,從預付餘額扣除。代理的外部市集端點會收到你的任務輸入,伺服器也會在帳戶帳本記錄支出與用量。README 描述的是另一項服務(端點保障觀測站),與清單不一致,連線前請先確認。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Imperium Workflow Studio — Multi-Agent DAG & Pipeline Executor,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/dev.agentdiet%2Fworkflows/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": {
    "imperium-workflow-studio-multi-agent-dag": {
      "type": "http",
      "url": "https://workflows.agentdiet.dev/mcp"
    }
  }
}

README

Assay — A2A & MCP Provider Assurance Observatory

[Assay Badge]

Live Observatory: https://assay-207908449630.us-central1.run.app

Assay continuously probes remote MCP, A2A, and x402 endpoints to verify liveness, pin canonical SHA-256 tools/list schema hashes (detecting silent MCP Rug Pulls), and scan for prompt-injection tool poisoning before your agent pays or executes a tool.

MCP Endpoint

  • Streamable HTTP MCP: https://assay-207908449630.us-central1.run.app/mcp
  • Pre-Flight REST API: POST https://assay-207908449630.us-central1.run.app/v1/preflight
  • Live Leaderboard: GET https://assay-207908449630.us-central1.run.app/v1/leaderboard

來源:README.md,提交 fd42696

工具

4

search_x402_mcp_marketplace

Search x402 mcp marketplace

Search 490+ indexed MCP and HTTP 402 (x402) tools by capability keyword and return ranked endpoints with pricing, trust scores, and SLA tiers. WHEN TO USE: Call first to discover which native slug or external endpoint matches your task before calling execute_marketplace_tool. WHEN NOT TO USE: Do not use to execute a tool directly (use execute_marketplace_tool or execute_workflow_bundle). PARAMETER INTERACTIONS: Pass capability keywords or a domain in query; omit agent_id and tx_hash (this discovery tool is always free and never consumes a free trial call). Example: search_x402_mcp_marketplace(query='example')

輸入參數query必填tx_hashagent_id

execute_marketplace_tool

Execute marketplace tool

Execute any of the 16 native AgentDiet B2A tools by slug or proxy an external marketplace tool URL ($0.001-$0.02 per call). WHEN TO USE: Call to run a single tool discovered via search_x402_mcp_marketplace; use execute_workflow_bundle when you want to run a 4-tool composite bundle in parallel. WHEN NOT TO USE: Do not use for catalog search (use search_x402_mcp_marketplace) or wallet checks (use get_agent_wallet_status). PARAMETER INTERACTIONS: Set target_tool to a native slug (e.g. 'distill', 'token-intel', 'sec-intel', 'github-audit') or external https:// URL, and pass its primary input in input_value. Omit agent_id and tx_hash during your 5 free calls. Read-only and idempotent; results are cached for 1 hour (<5ms cache hit). Pricing: the first 5 calls per agent_id are free and failed calls are never charged. After 5 calls, the tool returns a payment-required quote (not a fatal error) with a $2 Stripe top-up link and Base/Solana USDC addresses; complete payment, then retry with your agd_pass_ key in agent_id or pass tx_hash. Example: execute_marketplace_tool(target_tool='example')

輸入參數tx_hashagent_idinput_value必填target_tool必填

execute_workflow_bundle

Execute workflow bundle

Execute a 4-tool native workflow bundle in parallel in a single call ($0.015-$0.03) and return a unified dossier, saving 3 LLM round-trips. WHEN TO USE: Call for comprehensive multi-source due diligence on a token, company domain, repository, or research topic; use execute_marketplace_tool when you only need a single tool. WHEN NOT TO USE: Do not use for single-endpoint queries or free catalog search. PARAMETER INTERACTIONS: Select bundle_id first and provide the matching entity identifier (token/0x address, domain, repo, or URL) in target. Omit agent_id and tx_hash during your 5 free calls. Read-only and idempotent; results are cached for 1 hour (<5ms cache hit). Pricing: the first 5 calls per agent_id are free and failed calls are never charged. After 5 calls, the tool returns a payment-required quote (not a fatal error) with a $2 Stripe top-up link and Base/Solana USDC addresses; complete payment, then retry with your agd_pass_ key in agent_id or pass tx_hash. Example: execute_workflow_bundle(bundle_id='example')

輸入參數targettx_hashagent_idbundle_id必填

get_agent_wallet_status

Get agent wallet status

Inspect an agent's account ledger: remaining free trial calls (out of 5), prepaid USD balance, cumulative spend, total API calls, and total LLM tokens saved. WHEN TO USE: Call before a batch of paid tool executions or after completing a Stripe or USDC top-up to confirm your balance. WHEN NOT TO USE: Do not use to process web content, execute marketplace tools, or submit payments; use the other tools on this server for execution. PARAMETER INTERACTIONS: Omit agent_id to inspect the default trial account derived from your client IP, or pass your explicit agent_id or agd_pass_ session key to check a specific funded wallet. Free and read-only: never charges a fee or consumes a free trial call. Example: get_agent_wallet_status(agent_id='example')

輸入參數agent_id

版本歷史

2
  1. v7.0.17最新Oct 21, 2026
  2. v7.0.16Oct 21, 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 Agentdiet 整合