Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-mail-notifier Send a notification for iOS build completion"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
将 mcp-mail-notifier 项目的邮件通知功能转换为 Augment 可用的 MCP (Model Context Protocol) 工具。
📧 邮件通知: 发送任务完成通知到指定邮箱
⏱️ 时间跟踪: 自动计算任务耗时
🎯 项目集成: 专为 mcp-mail-notifier 项目定制
🔧 MCP 兼容: 完全兼容 Augment 的 MCP 协议
✅ QQ邮箱优化: 专门优化QQ邮箱SMTP配置
✅ 中文支持: 中文时区和格式化支持
Related MCP server: MiniMail MCP Server
cd mcp-tools
npm install登录QQ邮箱 (https://mail.qq.com)
点击"设置" -> "账户"
找到"POP3/IMAP/SMTP/Exchange/CardDAV/CalDAV服务"
开启"IMAP/SMTP服务"
获取授权码（不是QQ密码）
export QQ_EMAIL_USER="your-email@qq.com"
export QQ_EMAIL_AUTH_CODE="your-auth-code"如果不设置环境变量，将使用默认配置。
npm startnode send-notification.js "任务标题" "任务结果" "详细信息" "开始时间"示例：
node send-notification.js "iOS应用编译" "成功" "编译完成，所有测试通过" "2024-01-01 10:00:00"在 Augment 中配置 MCP 连接：
{
"mcpServers": {
"mcp-mail-notifier": {
"command": "node",
"args": [
"/path/to/your/project/mcp-tools/mcp-server.js"
],
"env": {
"QQ_EMAIL_USER": "your-qq-email@qq.com",
"QQ_EMAIL_AUTH_CODE": "your-authorization-code"
}
}
}
}发送任务完成通知邮件。
参数：
task_title (必需): 任务标题
task_result (必需): 任务结果
details (可选): 详细信息
recipient (可选): 收件人邮箱
start_time (可选): 任务开始时间
示例：
{
"task_title": "iOS项目文件结构重构",
"task_result": "成功完成",
"details": "已成功重构项目文件结构，创建Core目录统一管理核心组件",
"start_time": "2025-09-07 00:30:00"
}设置任务开始时间，用于后续计算任务耗时。
参数：
start_time (可选): 任务开始时间，不提供则使用当前时间
格式化时间间隔显示。
参数：
seconds (必需): 秒数
在 send-notification.js 中的 PROJECT_CONFIG 部分：
const PROJECT_CONFIG = {
name: 'mcp-mail-notifier',
displayName: '📒【mcp-mail-notifier】',
description: 'mcp-mail-notifier iOS应用'
};在 send-notification.js 中的 EMAIL_CONFIG 部分：
const EMAIL_CONFIG = {
recipient: 'xxx@qq.com',
sender: {
user: process.env.QQ_EMAIL_USER || 'xxx@qq.com',
authCode: process.env.QQ_EMAIL_AUTH_CODE || 'your-auth-code'
}
};启动 MCP 服务器：
npm start在 Augment 中配置 MCP 连接，指向这个服务器
使用工具：
send_notification: 发送通知邮件
set_task_start_time: 设置任务开始时间
format_duration: 格式化时间显示
npm run devnpm testnpm run install-globalnpm run uninstall-globalMCP SDK: 使用 @modelcontextprotocol/sdk 实现 MCP 协议
邮件服务: 使用 nodemailer 发送邮件
ES6 模块: 使用现代 JavaScript 模块系统
Node.js: 要求 Node.js 18+ 版本
535 Login Fail错误
确认已开启IMAP/SMTP服务
确认使用的是授权码而不是QQ密码
环境变量未设置
检查QQ_EMAIL_USER和QQ_EMAIL_AUTH_CODE是否正确设置
网络连接问题
确认网络可以访问smtp.qq.com:587
MCP 连接问题
确认 MCP 服务器正常启动
检查 Augment 配置文件路径正确
设置环境变量启用调试：
export DEBUG=nodemailer:*不要将授权码提交到版本控制系统
定期更换授权码
使用环境变量存储敏感信息
MIT License
欢迎提交 Issue 和 Pull Request！
格式化时间间隔显示
| Name | Required | Description | Default |
|---|---|---|---|
| seconds | Yes | 秒数 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden, yet it only says it formats a time interval. It does not disclose the resulting string format (e.g. '1h 30m' vs '01:30:00'), rounding behavior, or locale, which is the single most important thing to know about a pure formatting function.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single short phrase, front-loaded with the verb and resource and free of padding. Brevity here reflects under-specification rather than wasted words, but there is genuinely nothing redundant to trim.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
There is no output schema, so the description is responsible for conveying the shape of the returned display string, and it does not. For a tool whose entire value is the produced format, this leaves a significant gap in what an agent needs to use the result correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the sole parameter 'seconds' is already documented in the schema. The description adds no extra semantics (no unit clarification beyond the schema, no range constraints), so the baseline of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description ('格式化时间间隔显示') essentially restates the tool name format_duration, adding only the word 'interval' where the name says 'duration'. It gives no hint of the output format or the unit/convention used, so an agent cannot distinguish what this produces versus a generic formatting helper.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to call this tool versus alternatives, no mention of acceptable input ranges, and no note of what happens with negative or fractional seconds. The sibling tools (send_notification, set_task_start_time) are unrelated, so no routing is needed, but the description offers no usage context at all.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
发送任务完成通知邮件到指定邮箱
| Name | Required | Description | Default |
|---|---|---|---|
| details | No | 详细信息（可选） | |
| recipient | No | 收件人邮箱（可选，默认使用配置中的邮箱） | |
| start_time | No | 任务开始时间（可选，格式：YYYY-MM-DD HH:mm:ss） | |
| task_title | Yes | 任务标题 | |
| task_result | Yes | 任务结果（如：成功、失败、完成等） | |
| project_name | No | 项目名称（可选，用于邮件标题，默认使用 mcp-mail-notifier） | mcp-mail-notifier |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the external side effect of actually sending an email but omits whether this requires configured credentials, whether delivery is synchronous, whether it is retried on failure, and what the tool returns. The wording '完成通知' (completion notification) also undersells that task_result can carry failure states.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single front-loaded sentence with no padding. It is efficient, though it is arguably too terse for a side-effect-bearing tool rather than being wasteful.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool that performs an external, irreversible action (sending email) with no annotations and no output schema, the description is incomplete. It does not cover configuration prerequisites, failure behavior, or return expectations that an agent needs to invoke it safely.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so all six parameters are already documented in the schema; the baseline is 3. The description only echoes the recipient concept ('指定邮箱') and adds no format, default, or constraint details beyond what the schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb (发送/send) and resource (任务完成通知邮件/task-completion notification email) with a clear target (指定邮箱). It is distinguishable from siblings like set_task_start_time and format_duration, though it does not explicitly name them as alternatives.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no when-to-use or when-not-to-use guidance. The description does not state prerequisites (e.g., that mail configuration must exist) or any condition under which the agent should prefer a different tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
设置任务开始时间，用于后续计算任务耗时
| Name | Required | Description | Default |
|---|---|---|---|
| start_time | No | 任务开始时间（可选，格式：YYYY-MM-DD HH:mm:ss，不提供则使用当前时间） |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It does not disclose whether setting the start time overwrites a prior value, whether the operation is idempotent, what permissions are needed, or what happens on the backend—only the downstream purpose is stated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single front-loaded sentence with no filler; the action and its rationale are packed efficiently into one clause pair. Slightly terse relative to what a mutation tool could convey, but nothing is wasted.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a one-optional-param setter with 100% schema coverage and no output schema, the description covers the essentials. However, with zero annotations the missing details on overwrite behavior and idempotency leave a real gap for a write operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%: the single start_time parameter already documents the expected format (YYYY-MM-DD HH:mm:ss) and the fallback to current time. The description adds no parameter-level meaning beyond the schema, so the baseline of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb ('设置' / set) and resource (任务开始时间 / task start time) plus the downstream purpose (calculating task duration). The sibling tools (send_notification, format_duration) are unrelated enough that no explicit differentiation is needed, but it doesn't delineate itself against anything.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is only implied: the phrase '用于后续计算任务耗时' suggests the start time is set so duration can later be computed, but there is no explicit when-to-use, when-not-to-use, or mention of alternatives like format_duration for the computation step.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0format_durationsend_notificationset_task_start_timeScored across 3 tools
The three tools have clearly distinct purposes: sending an email notification, setting a task start time, and formatting a duration. No two tools overlap in action or target resource.
All tool names use a consistent snake_case verb_noun pattern: send_notification, set_task_start_time, format_duration. The convention is predictable and easy to parse.
Three tools are a reasonable, lightweight surface for a mail notifier. Two are timing helpers rather than direct mail operations, so the set is slightly narrow but not inappropriate.
The core send_notification tool is present, and duration helpers exist, but there is no tool to retrieve or clear the stored start time or to calculate/embed elapsed duration into the notification. Other notification scenarios are also absent.
Email infrastructure for AI agents — send, receive, search, and reply to email over MCP.
MCP protocol requiring task acceptance and provenance tags. Self-hosted only - see README.
Manage Timequip projects, tasks, comments, members, and dashboards through MCP.
MCP server for MailTempo's public free temporary email inboxes.
