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.
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.
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), nothttp— this is mcpjungle-specific.
Note:
host.docker.internaldoes 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
/tmpas 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
License
MIT — Nícolas Pastorello
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。