Agent Email List — Free SMTP Relay for AI Agents

Free transactional email + SMTP relay. Agents self-signup, no API key needed to start.

我该使用它吗

质量与安全性

A
描述质量
100%
模式完整度
83%
命名质量
100%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

基于对工具定义和协议合规性的自动分析。

上下文开销

~879token 数(工具定义)
~670 B典型响应大小
对注意力有中等影响(占 128k 上下文窗口的 0.69%)

这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。

安装

一键安装

将以下内容添加到你的 `claude_desktop_config.json` 文件中:

{
  "mcpServers": {
    "free-transactional-email-smtp-relay": {
      "url": "https://ai.agentemaillist.com/mcp"
    }
  }
}

远程端点

https://ai.agentemaillist.com/mcpstreamable-http

它能做什么

工具清单

工具(8)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟡create_account(name, password, email)

Create an account on this email service and get an API key back. Needs no existing credentials, so an agent with nothing can call this first. The key is returned once and never again. Free, with no card and no trial clock.

输入模式

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "Optional display name."
    },
    "password": {
      "type": "string",
      "description": "At least 12 characters. Needed only to sign in to the web console."
    },
    "email": {
      "type": "string",
      "description": "A contact address for the account."
    }
  },
  "required": [
    "email",
    "password"
  ]
}
🟢list_domains

List the sending domains on this account, with their verification state and how much of today's sending allowance each has left.

输入模式

{
  "type": "object",
  "properties": {}
}
🟡add_domain(name)

Register a domain to send from, and get the DNS records that must be published before it will work. Publishing DNS usually needs a human with registrar access, so start this early. The domain cannot send until verify_domain succeeds.

输入模式

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "A bare domain such as mail.yourcompany.com. A subdomain is better than the root."
    }
  },
  "required": [
    "name"
  ]
}
🟢verify_domain(name)

Re-read DNS now and mark the domain active if its SPF and DKIM records are visible. DNS takes minutes to hours to propagate; poll this every few minutes, not every few seconds.

输入模式

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string"
    }
  },
  "required": [
    "name"
  ]
}
🟡send_email(domain, text, from, to, html, ...)

Send a message. The domain must be verified and the from address must belong to it. Counts one against the daily allowance per recipient. Set test_mode true to run the whole pipeline, including content screening, without sending anything and without spending allowance — do that first when building.

输入模式

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string",
      "description": "The verified domain to send from."
    },
    "text": {
      "type": "string",
      "description": "Plain text body."
    },
    "from": {
      "type": "string",
      "description": "An address at that domain."
    },
    "to": {
      "type": "string",
      "description": "One address, or several separated by commas."
    },
    "html": {
      "type": "string",
      "description": "Optional HTML body."
    },
    "subject": {
      "type": "string"
    },
    "test_mode": {
      "type": "boolean",
      "description": "Accept and screen the message but send nothing. Defaults to false."
    }
  },
  "required": [
    "domain",
    "from",
    "to"
  ]
}
🟡get_sending_limits(domain)

How much this domain may send today and what graduates it to the next rung, plus this account's standing: how many domains it may hold and whether sending is paused. New domains start at a low daily cap and climb as they prove themselves, so check this before planning a bulk send rather than discovering it part-way. Call it with no domain for the account-level answer alone.

输入模式

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string",
      "description": "Optional. Omit for account limits without a domain's allowance."
    }
  }
}
🟢list_messages(domain, limit, direction, folder)

Recent messages for a domain, sent and received. Use direction to filter, and folder to separate inbox from spam on received mail.

输入模式

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string"
    },
    "limit": {
      "type": "integer",
      "description": "Up to 100. Defaults to 25."
    },
    "direction": {
      "type": "string",
      "enum": [
        "outbound",
        "inbound"
      ]
    },
    "folder": {
      "type": "string",
      "enum": [
        "inbox",
        "spam"
      ]
    }
  },
  "required": [
    "domain"
  ]
}
🟡get_delivery_events(domain, limit, event, recipient)

What happened to messages on this domain: accepted, delivered, failed, and so on. A send returning success means queued, not delivered; this is where the delivery outcome actually appears.

输入模式

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string"
    },
    "limit": {
      "type": "integer"
    },
    "event": {
      "type": "string",
      "description": "Filter to one type, such as delivered or failed."
    },
    "recipient": {
      "type": "string"
    }
  },
  "required": [
    "domain"
  ]
}

社区

评价此服务器

证据

最近观测

已验证未记录版本8 个工具
已验证未记录版本8 个工具