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)
Test inboxes for AI agents testing your app: block until the OTP or magic link arrives.
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。
MAILSOCKET_API_KEY, MAILSOCKET_BASE_URL, Authorization标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
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 …”。
这个地址需要在请求的 header 中放入密钥,而添加连接器的菜单无法设置。请改用 Claude Code、Cursor 或 VS Code。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"mailsocket": {
"command": "uvx",
"args": [
"mailsocket-mcp"
],
"env": {
"MAILSOCKET_API_KEY": "your-value",
"MAILSOCKET_BASE_URL": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add --transport http mailsocket https://mcp.mailsocket.app/mcp --header 'Authorization: your-value'claude mcp add mailsocket --env MAILSOCKET_API_KEY=your-value --env MAILSOCKET_BASE_URL=your-value -- uvx mailsocket-mcp运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"mailsocket": {
"url": "https://mcp.mailsocket.app/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"mailsocket": {
"command": "uvx",
"args": [
"mailsocket-mcp"
],
"env": {
"MAILSOCKET_API_KEY": "your-value",
"MAILSOCKET_BASE_URL": "your-value"
}
}
}
}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": {
"mailsocket": {
"type": "http",
"url": "https://mcp.mailsocket.app/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"mailsocket": {
"type": "stdio",
"command": "uvx",
"args": [
"mailsocket-mcp"
],
"env": {
"MAILSOCKET_API_KEY": "your-value",
"MAILSOCKET_BASE_URL": "your-value"
}
}
}
}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。
这个地址需要在请求的 header 中放入密钥,而添加连接器的菜单无法设置。请改用 Claude Code、Cursor 或 VS Code。
你的选择通过 Cookie 保存在这台设备上,无需账户。
MAILSOCKET_BASE_URL envAuthorization 机密 必填 HTTP header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。
我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。
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6日
注册名称已通过域名 mailsocket.app 验证(注册中心会核实域名所有权)
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
尚未检查;我们会轮流检查各个端点
尚未检查;我们会轮流检查各个端点
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 1 项适用的基础检查中通过了 1 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。
你需要填写:MAILSOCKET_API_KEY, Authorization
两种方式都可以:安装在你的电脑上,或者连接云端版本。
GitHub 仓库最后更新于–,最新版本(0.4.2)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, zanadir
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.
Find what a repository's CI is missing, and which security checks cannot fail the build.
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。
An MCP server that exposes mailsocket to AI coding agents as native tools, so an agent can create a per-test inbox and block on the OTP or magic link without writing any polling code. For testing apps you own or are authorized to test. Not for creating accounts on services you don't control.
It wraps the Python SDK — no second HTTP client, no re-implemented polling.
| Tool | What the agent gets |
|---|---|
create_inbox(label?) | a fresh inbox id + address |
wait_for_otp(inbox_id, timeout?=60, min_confidence?=0, since?) | the headline — blocks (bounded: requested deadline clamped to 120s locally, 55s on the remote server) and returns the OTP string + confidence + subject/from/id/received_at. Default since omitted: only messages arriving after this call are matched. |
wait_for_link(inbox_id, timeout?=60, since?) | the extracted magic link (returned, *not* followed) + subject/from/id/received_at. Default since omitted: only messages arriving after this call are matched. |
list_inboxes(limit?, cursor?) | one page of inboxes owned by the key (server default page size 25) + next_cursor/has_more |
list_messages(inbox_id, has_otp?, subject_contains?, sender?, limit?, cursor?) | one page of messages, optionally filtered (server default page size 25) + next_cursor/has_more |
get_latest(inbox_id) | the newest message, without blocking |
send_test_code(inbox_id) | puts one sample OTP email straight into the inbox (no mail server) and returns its message_id + sent_at, so you can check the wait loop without real email. 5 per inbox / 20 per account per hour. |
delete_inbox(inbox_id) | remove an inbox when done |
Errors from the SDK (AuthError / NotFound / RateLimited / WaitTimeout) are turned into clean MCP tool errors — no stack traces, and the API key is never echoed back.
create_inbox needs no since — a fresh inbox only ever has new messages. By default, wait_for_otp/wait_for_link omit since entirely, so the server matches only messages arriving AFTER the call (the request start time). But if you reuse an existing inbox (e.g. to request a second OTP/link), pass since explicitly: otherwise a call with no since will correctly ignore anything already sitting in the inbox, which is right for most reuse, but if you actually WANT to catch a code that already arrived before you called the tool, pass either the time right before you triggered the new email (ISO8601 or unix seconds), or the id of the last message you saw (msg_..., meaning "only messages after that one") — both tools return id/received_at on the matched message so you can chain since= into the next call on that same inbox.
send_test_code does not go through the mail server, so the code is already in the inbox when the tool returns. Take a cutoff first: the id from get_latest (or since=0 if the inbox is empty), or the current time. Then call send_test_code(inbox_id), then wait_for_otp(inbox_id, since= ). Without since the wait only sees mail that arrives during the wait, so it would miss the test code.
POST /api/v1/agents/register.No install needed with uv:
uvx mailsocket-mcp
Or install with pip:
pip install mailsocket-mcp
mailsocket-mcp
Either way, it reads MAILSOCKET_API_KEY (and optional MAILSOCKET_BASE_URL) from the environment. If the key is missing it exits with a clear message and status 2; the key is never logged.
Add this to your client's MCP config file — claude_desktop_config.json for Claude Desktop, ~/.cursor/mcp.json for Cursor:
{
"mcpServers": { "mailsocket": { "command": "uvx", "args": ["mailsocket-mcp"], "env": { "MAILSOCKET_API_KEY": "ms_live_..." } } } }
claude mcp add mailsocket -e MAILSOCKET_API_KEY=ms_live_... -- uvx mailsocket-mcp
Any other MCP-compatible client works the same way: point it at the mailsocket-mcp executable (or uvx mailsocket-mcp) over stdio and pass the key through the environment.
The same tools are hosted at `https://mcp.mailsocket.app/mcp` over Streamable HTTP. Send your key on every request as a header: Authorization: Bearer ms_live_.... Never put the key in the URL; a ?api_key= request is rejected.
claude mcp add --transport http mailsocket https://mcp.mailsocket.app/mcp \
--header "Authorization: Bearer ms_live_..."
~/.cursor/mcp.json){
"mcpServers": { "mailsocket": { "url": "https://mcp.mailsocket.app/mcp", "headers": { "Authorization": "Bearer ms_live_..." } } } }
.vscode/mcp.json){
"servers": { "mailsocket": { "type": "http", "url": "https://mcp.mailsocket.app/mcp", "headers": { "Authorization": "Bearer ms_live_..." } } } }
Any client that can set a custom HTTP header works the same way (OpenAI Agents SDK, the n8n MCP Client node, your own code).
Things to know:
wait_for_otp / wait_for_link wait at most 55s per call, which keeps each response under proxy timeouts. On a timeout, call the tool again.mailsocket-mcp-http runs the same server (see mailsocket_mcp/remote.py for its env vars).| Variable | Required | Description |
|---|---|---|
MAILSOCKET_API_KEY | yes (secret) | Your mailsocket API key (ms_live_...). |
MAILSOCKET_BASE_URL | no | Override the API base URL. Defaults to https://dash.mailsocket.app/api/v1. |
pip install -e ".[dev]"
pytest
Tests make no external or live-API requests. The SDK client is faked, and the remote-transport tests talk to a local fake upstream on 127.0.0.1.
mailsocket>=0.3.1: wait_for_otp / wait_for_link called without since no longer miss a message that lands between the SDK's internal long-poll calls (each follow-up call sends the cutoff the server reported in Mailsocket-Wait-Since). No tool signature changes.send_test_code(inbox_id) tool (stdio and the hosted remote server, under the same per-key caps as the other non-wait tools): puts one sample OTP email into your own inbox without going through the mail server. Requires mailsocket>=0.3.0 (Client.send_test_code).mailsocket>=0.2.0): wait_for_otp / wait_for_link now omit since by default instead of forwarding 0 ("any message already in the inbox"). The old default could return a STALE OTP/link already sitting in a reused inbox; the new default matches only messages arriving after the call. Pass since=0 explicitly to keep the old behaviour. Hosted server (mcp.mailsocket.app, deployed from the repo, no new PyPI release): per-key concurrent waits raised 3 → 10 (= the Pro plan cap; the API still enforces each plan's own cap) and the shared wait pool 16 → 32, following the backend's raised wait capacity (global 64).wait_for_otp / wait_for_link accept an optional since (ISO8601, unix seconds or a message id) so a reused inbox returns the NEW code; results include the message id and received_at.mailsocket>=0.1.3 (stricter _seg id validation in the underlying Python SDK).