Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者提供的说明(英文原文)
Buy products and services with escrow, or trade crypto P2P. Money moves only with human 2FA.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
适用于网页版、桌面版和手机版 Claude:
https://api.iescrow.io/mcp在终端中运行这条命令
claude mcp add --transport http iescrow https://api.iescrow.io/mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"iescrow": {
"url": "https://api.iescrow.io/mcp"
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"iescrow": {
"type": "http",
"url": "https://api.iescrow.io/mcp"
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
ChatGPT 只能连接互联网上的服务器:
https://api.iescrow.io/mcp菜单名称可能因套餐和版本不同而略有差异。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
服务器要求先登录,才会列出它的工具。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
注册名称已通过 GitHub 账户 iEscrow 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
在 416 毫秒内响应(HTTP 401)
声明支持 OAuth 登录,你的 AI 应用可以带你去登录
尚未检查;我们会在检查端点时读取工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于–,最新版本(0.3.1)于5天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
同一分类中有:Spec Driven Development, Remote Desktop Commander, AvaHR
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Read hiring data and create inactive assessment and questionnaire drafts for human review.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
iEscrow is a cryptocurrency escrow platform: in every trade the crypto is held by iEscrow until both sides have delivered, so nobody has to hand over first. This repository documents the iEscrow MCP server, which lets an AI agent (Claude, ChatGPT or any MCP host) operate an iEscrow account on behalf of the user who authorized it.
https://api.iescrow.io/mcphttps://api.iescrow.io), PKCE, dynamic client registrationThe agent can quote, open trades, read balances and states, and prepare marketplace ads. Anything that moves money is not executed by the agent: the tool creates an approval and returns a link. The account owner opens that link, sees exactly what is about to happen, and approves it with their two-factor code.
What the agent can never do, by design:
The API enforces this with an allow-list of routes for agent tokens; the MCP server only wraps those routes.
An iEscrow account with:
The connection screen (/connect) checks the three before issuing a token. Trades can be executed by an agent only in the countries where iEscrow is enabled for agents; get_readiness tells you which.
Settings → Connectors → *Add custom connector* → name iEscrow, URL https://api.iescrow.io/mcp. Claude discovers the authorization server, opens the iEscrow consent screen, and the connection is ready once you approve it.
claude mcp add --transport http iescrow https://api.iescrow.io/mcp
Then run /mcp inside Claude Code to complete the login.
Settings → Connectors → *Create* (developer mode) → name iEscrow, MCP server URL https://api.iescrow.io/mcp, authentication *OAuth*. ChatGPT registers itself as a client and sends you to the iEscrow consent screen.
Point the host to the URL above with the Streamable HTTP transport. The server publishes /.well-known/oauth-protected-resource, and the authorization server publishes /.well-known/oauth-authorization-server; hosts that implement the MCP authorization spec need nothing else. See examples/ for configuration snippets.
| Scope | Grants |
|---|---|
profile:read | who the user is and whether the account is ready to trade |
quotes:read | executable offers and prices on the marketplace |
wallet:read | balances and masked payment accounts |
trades:read | state of the user's trades and ads |
trades:write | open trades, request approvals to lock crypto or confirm payments, cancel own requests |
ads:write | prepare marketplace ads (always subject to the human's approval) |
Scopes are chosen on the consent screen and can be revoked at any time from *Connected apps* in the user's iEscrow settings.
Per connection: 60 calls per minute, 10 openings per hour (taking a marketplace offer, requesting a private escrow or buying from the catalog), 20 money-moving approval requests per hour. One concurrent long-poll (wait_for_trade_update) per user. A limited call returns error_key and retry_after_s.
get_readiness — confirm the account can trade.get_quote with side=buy, the crypto, the fiat and the amount — pick an offer; note compatible_account_ids.open_trade with the offer id, the amount and a compatible payment_account_id.get_trade — wait until crypto_funded is true. The human must not pay before that.get_proof_upload_link — give the user the link; it shows the exact amount (the cents are the payment key) and the account to pay. The user pays, attaches the receipt and declares the payment there.wait_for_trade_update — the trade moves to released when the seller confirms. The crypto is now in the user's iEscrow balance.Selling is the mirror image: open_trade with side=sell, then fund_escrow (the human approves the lock by link), then confirm_received once the fiat arrives (again approved by link).
Swapping one crypto for another is shorter, because no bank is involved and nobody has to confirm a transfer: get_swap_quote, then open_trade with the offer's open_trade_args, then fund_escrow. Both legs are verified on chain and the escrow settles by itself once each side has funded.
To deal with one specific person instead of the market, use open_private_request (a product or a service, paid milestone by milestone if you want) or open_private_swap. Both need that person's reference number, which they share with you from their own account, so ask the user for it rather than guessing: that requirement is what keeps an agent from firing requests at a list of usernames.
Every error is returned as structured content with error: true, an HTTP-like status, a stable error_key and a human-readable message. When an action needs the human, the response carries approval_required: true and approval.approve_url; poll check_approval with approval.public_id to learn the outcome.
The MCP server never opens the database and holds no secrets of its own: it verifies the user's access token (RS256, issuer and audience pinned) and forwards the same bearer to the API. Reports about the agent channel: contact@iescrow.io.
This repository holds the public documentation of the server and the manifest used to list it in MCP registries. The server's source code is not published here.