Epinu

ai.epinu由 epinu.ai 發布官方發布者v1.0.4更新於 Oct 25, 2026

Agent-first marketplace for real-world assets — agro and energy first; humans approve every write.

已驗證Streamable HTTP可網頁執行網頁搜尋與抓取商業與電商

概覽

AI 產生的概覽

Epinu 是面向真實世界資產、以代理為優先的交易市場託管 MCP 端點,讓助理搜尋公開專案與商品並讀取完整記錄

可以做什麼
搜尋 Epinu 公開專案以及設備、服務和資產的市場商品,或透過統一的唯讀搜尋同時查詢兩者,並依結果 id 取得完整文件。閱讀平台概覽、提案/審核模式和代理行為準則的靜態說明。持有委派權杖時,可將交易草擬為待審核提案,須經人工核准後才會寫入。
適用情境
當助理需要查詢真實世界資產專案或市場商品(農業、能源、設備、工業服務)並閱讀詳細內容時使用;或帳號擁有者希望由代理準備商品或專案提案供人工審核時使用。
執行需求
遠端 Streamable HTTP 端點,不需要本機執行環境或套件。唯讀搜尋與取得可匿名使用,無需帳號或權杖。草擬提案需要 Epinu 帳號,並以 Authorization Bearer 標頭提供委派的 epagt_ 權杖。
安裝前請注意
寫入不會直接執行:寫入工具只建立狀態為待審核的提案並回傳 approval_url,由人工在儀表板核准或拒絕,未核准的提案 7 天後過期。epagt_ 權杖有作用域限制,應妥善保密;超出範圍的呼叫會失敗,刪除或資料變更等敏感操作在審核時還需人工重新進行 MFA。提案會在稽核記錄中記錄代理的用戶端 id。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Epinu,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/ai.epinu%2Fepinu/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": {
    "epinu": {
      "type": "http",
      "url": "https://api.epinu.ai/api/agent/mcp"
    }
  }
}

README

Epinu MCP — agent door for a real-world asset marketplace

[MCP endpoint liveness]

Epinu is an agent-first marketplace for real-world assets — agro and energy first, extending to mining, equipment, and industrial services. AI agents are first-class users: they can search, read, and draft deals directly over MCP, and every write goes through a human-approval broker with a full audit trail.

This is the public integration repository for Epinu's hosted MCP endpoint: registry metadata (ai.epinu/epinu in the official MCP Registry), runnable examples, and operational checks. The Epinu platform implementation is maintained separately.

Try it in 60 seconds — no account, no token

bash
bash examples/quickstart.sh

That queries the live public production endpoint anonymously and returns current public project and marketplace results. The sample queries currently surface an ASIC repair center in Odessa, TX and related services; inventory may change. (QA fixtures are excluded from public reads as of 2026-07-15.) The anonymous tier allows initialize, tools/list, and five read tools (getting_started, marketplace_listings_search, projects_search, search, and fetch) against public data — see TOOLS.md for the reference.

Or the same flow in plain Node (zero dependencies, Node ≥ 18):

bash
node examples/walkthrough.mjs

Connect from Claude Code / any MCP client

bash
claude mcp add --transport http epinu https://api.epinu.ai/api/agent/mcp

or in .mcp.json:

json
{  "mcpServers": {    "epinu": {      "type": "http",      "url": "https://api.epinu.ai/api/agent/mcp"    }  }}

Works immediately in read-only mode. To let your agent draft deals, add "headers": {"Authorization": "Bearer epagt_..."} with a delegated token — see below for how to get one. Details in examples/claude-code.md.

The interesting part: writes never execute

Epinu's write tools (marketplace_listing_create, project_create, …) do not write to the database. They create proposals (status: pending) and return an approval_url. A human reviews the proposal in the Epinu dashboard and approves or rejects it — only approval executes the change.

examples/walkthrough.mjs demonstrates the agent-controlled portion of the flow: search → create a pending proposal → check its status. Human approval happens separately in the Epinu dashboard. examples/walkthrough.md is the recorded, redacted transcript of a real production run — proposal created, reviewed, and rejected by the human, with nothing ever written.

Why is every write human-approved?

  • Agents make mistakes; markets are real. A hallucinated listing, a wrong price, or a duplicate is cheap to reject at proposal time and expensive to unwind after it's live. The broker makes the failure mode "a human clicked reject", not "a bad write hit production".
  • Identity and audit. Every proposal records actor.type=personal_agent and the agent's client id. The human always knows which agent proposed what, and the trail survives.
  • Scoped delegation, not account takeover. An epagt_ token is created by the account owner with explicit scopes (Dashboard → Settings → Authorize Agent). Out-of-scope calls fail with a clean scope error. Sensitive actions (deletes, profile changes) additionally require fresh MFA on the human side at approval time.
  • Drift checks. If the underlying data changed materially between proposal and approval, approval is blocked or requires explicit acknowledgment — an agent can't get a stale change approved.
  • Unapproved proposals expire on their own (7 days).

Production experience: Epinu reports that its first external marketplace participant was onboarded through a delegated AI agent: the agent prepared the catalog proposals, and the account owner reviewed and approved them in the dashboard. A sanitized case study is forthcoming.

Getting a token (for writes)

  1. Create an account at epinu.ai/signup
  2. Dashboard → Settings → Authorize Agent → choose scopes → copy the epagt_ token, or send your agent's human to https://epinu.ai/authorize-agent?name=<AgentName>&scopes=<scopes>
  3. Use it as Authorization: Bearer epagt_... on POST /api/agent/mcp (the token is valid on the MCP endpoint only)

What's in this repo

FileWhat it is
server.jsonThe MCP Registry entry for ai.epinu/epinu
examples/quickstart.shAnonymous tier in 60 seconds (curl)
examples/walkthrough.mjsSearch → create pending proposal → check proposal status (Node, zero deps)
examples/walkthrough.mdRecorded, redacted transcript of a real production run
examples/claude-code.mdConnect from Claude Code / .mcp.json
TOOLS.mdAnonymous-tier tool reference with captured responses
SECURITY.mdHow to report a vulnerability

The canonical, always-current agent documentation lives on the site itself: llms.txt · .well-known/mcp. This repo deliberately links rather than mirrors, so it can't go stale.

License

Examples and docs in this repository: MIT. The Epinu platform itself is a hosted service — epinu.ai.

來源:README.md,提交 1a8ea2b

工具

5

getting_started

Getting Started

Start here: platform overview, the proposal/approval operating model, auth rules, common flows, and agent etiquette. Static content — requires no scopes.

無需輸入參數。

fetch

Fetch

Fetch the full document for one search result by its opaque id (project:<uuid> or listing:<uuid>). Returns { id, title, text, url, metadata }. Available without a token; public data only. Wraps projects_get_deep_dive and marketplace_listing_get. Unknown or malformed ids return a clean not-found.

輸入參數id必填

版本歷史

1
  1. v1.0.4最新Sep 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