Mail.tm MCP Server

Mail.tm MCP Server

Enables AI assistants to manage temporary email addresses via the mail.tm API, including creating disposable inboxes, reading messages, and managing accounts.

Category
访问服务器

README

Mail.tm MCP Server

An MCP (Model Context Protocol) server that lets AI assistants manage temporary email addresses via the mail.tm API. Create disposable inboxes, read messages, and manage accounts — all from your AI chat.

Docker Image GitHub release

Tools

Tool Description
list_domains List available domains for creating temp addresses
create_temp_email Create a new disposable email account (random or custom)
login Log in to an existing mail.tm account
get_inbox List messages in the current inbox (paginated)
read_email Read the full content of an email by ID
mark_as_read Mark a message as read
delete_email Permanently delete a message
get_account_info Get current account details and storage usage
delete_account Permanently delete the account and all its messages
logout Clear the current session without deleting the account

Transport

The server runs as a streamable-http MCP server on port 8000, endpoint /mcp.

Compatible with:

  • mcpjungle
  • Claude Desktop (HTTP mode)
  • Any MCP client that supports streamable-http

Quick Start

Docker Compose (recommended)

curl -O https://raw.githubusercontent.com/opastorello/mailtm-mcp-server/master/docker-compose.yml
docker compose up -d

Server available at http://localhost:8000/mcp.

Docker (manual)

docker pull ghcr.io/opastorello/mailtm-mcp-server:latest
docker run -d -p 8000:8000 -v mailtm-session:/tmp --name mailtm ghcr.io/opastorello/mailtm-mcp-server:latest

Local (no Docker)

pip install -r requirements.txt
python mailtm_server.py

Requires Python 3.11+.


Register with mcpjungle

Standalone (mcpjungle on the host)

cat > /tmp/mailtm.json << 'EOF'
{
  "name": "mailtm",
  "transport": "streamable_http",
  "url": "http://localhost:8000/mcp"
}
EOF

mcpjungle register -c /tmp/mailtm.json

mcpjungle running in Docker (same host)

When mcpjungle runs inside Docker, localhost doesn't resolve to the host. You need both containers on the same Docker network.

The included docker-compose.yml handles this automatically — it joins the opt_default network (mcpjungle's default network) and sets a fixed container name mailtm so the hostname never changes across restarts.

# Download and start
curl -O https://raw.githubusercontent.com/opastorello/mailtm-mcp-server/master/docker-compose.yml
docker compose up -d

# Register using the container hostname
cat > /tmp/mailtm.json << 'EOF'
{
  "name": "mailtm",
  "transport": "streamable_http",
  "url": "http://mailtm:8000/mcp"
}
EOF

mcpjungle register -c /tmp/mailtm.json

Note: The transport value is streamable_http (underscore), not http — this is mcpjungle-specific.

Note: host.docker.internal does not work on Linux. Use the container name or a fixed IP instead.

To re-register after changes:

mcpjungle deregister mailtm
mcpjungle register -c /tmp/mailtm.json

Invoke tools via mcpjungle CLI

mcpjungle invoke mailtm__create_temp_email
mcpjungle invoke mailtm__get_inbox
mcpjungle invoke mailtm__list_domains

Configure in Claude Desktop

Pointing to a running instance:

{
  "mcpServers": {
    "mailtm": {
      "url": "http://localhost:8000/mcp"
    }
  }
}

Session Management

The server stores the active session in /tmp/mailtm_session.json:

  • Session persists between tool calls automatically within the same run.
  • Mount /tmp as a Docker volume to survive container restarts.
  • logout() clears the session without deleting the account.
  • delete_account() deletes the account and clears the session.

Example Workflow

1. create_temp_email()           → generates a random address like abc123@dollicons.com
2. get_inbox()                   → check for new messages
3. read_email(message_id="...")  → read the content
4. delete_account()              → clean up when done

Dependencies

  • mcp[cli] >= 1.2.0 — FastMCP server framework
  • requests >= 2.31.0 — HTTP client for the mail.tm API

License

MIT — Nícolas Pastorello

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选