UnCorreoTemporal
Disposable email MCP server for autonomous AI agents. Create labeled temporary inboxes, wait for verification emails, extract OTP codes and confirmation links — zero human intervention required.
README
uncorreotemporal-mcp
MCP server for UnCorreoTemporal, focused on autonomous signup and email verification workflows.
Architecture Demo
AI Agent
|
| MCP
v
Temporary Email MCP Server
|
v
UnCorreoTemporal API
Quickstart (30 seconds)
uvx uncorreotemporal-mcp
Or run local project version:
UCT_API_KEY=uct_your_key_here \
uv run uncorreotemporal-mcp
Minimal Workflow Example
inbox = await create_signup_inbox("github")
email = await wait_for_verification_email(inbox["inbox_id"])
link = await extract_verification_link(
inbox_id=inbox["inbox_id"],
message_id=email["message_id"],
)
Public Tools
create_signup_inboxwait_for_verification_emailget_latest_emailextract_otp_codeextract_verification_linkcomplete_signup_flow
New v1 tool: complete_signup_flow
Runs:
- create inbox
- wait verification email
- extract verification link + OTP
Input:
{
"service_name": "github",
"timeout_seconds": 90,
"poll_interval_seconds": 3,
"subject_contains": "verify",
"from_contains": "noreply",
"preferred_domains": ["github.com"],
"ttl_minutes": 30
}
Output:
{
"status": "success",
"inbox_id": "agent42@uncorreotemporal.com",
"email": "agent42@uncorreotemporal.com",
"verification_message": {
"message_id": "msg-1",
"subject": "Verify your email",
"from_address": "noreply@example.com",
"received_at": "2026-03-08T11:30:00Z"
},
"verification_link": "https://example.com/confirm?t=abc",
"otp_code": "483920",
"link_candidates": ["https://example.com/confirm?t=abc"],
"otp_candidates": ["483920"]
}
status can be success, partial_success, or timeout.
Tool I/O summary
create_signup_inbox(service_name, ttl_minutes?)
Returns:
{
"inbox_id": "agent42@uncorreotemporal.com",
"email": "agent42@uncorreotemporal.com",
"expires_at": "2026-03-08T12:00:00Z",
"service_name": "github"
}
wait_for_verification_email(inbox_id, timeout_seconds?, poll_interval_seconds?, subject_contains?, from_contains?)
Returns:
{
"status": "received",
"message_id": "msg-1",
"received_at": "2026-03-08T11:30:00Z",
"subject": "Verify your account",
"from_address": "noreply@example.com",
"timeout_seconds": 90
}
get_latest_email(inbox_id, mark_as_read?)
Returns full message body and metadata.
extract_otp_code(message_text? | inbox_id+message_id, otp_length_min?, otp_length_max?)
Returns:
{
"otp_code": "483920",
"candidates": ["483920"]
}
extract_verification_link(message_text? | inbox_id+message_id, preferred_domains?)
Returns:
{
"verification_link": "https://example.com/confirm?t=abc",
"candidates": ["https://example.com/confirm?t=abc"]
}
Configuration
Environment variables:
UCT_API_KEY(required)UCT_API_BASE(optional, default:https://uncorreotemporal.com)UCT_HTTP_TIMEOUT_SECONDS(optional, default:20)UCT_MCP_TRANSPORT(optional,stdioby default; also supportsstreamable-httpandsse)UCT_MCP_HOST(optional, default:0.0.0.0)UCT_MCP_PORT(optional, default:8000)UCT_MCP_PATH(optional, default:/mcp)
Important: inbox_id == email address.
Examples
See /examples:
simple_workflow.pyopenai_agent_signup.pylangchain_agent_signup.pyagent_creates_account.py
Run dry-run:
uv run python examples/simple_workflow.py --dry-run
Docker
Build:
docker build -t uncorreotemporal-mcp .
Run stdio mode:
docker run --rm -i \
-e UCT_API_KEY=uct_your_key_here \
uncorreotemporal-mcp
Run streamable-http mode:
docker run --rm -p 8000:8000 \
-e UCT_API_KEY=uct_your_key_here \
-e UCT_MCP_TRANSPORT=streamable-http \
-e UCT_MCP_PATH=/mcp \
uncorreotemporal-mcp
Breaking Changes
Removed legacy low-level tools:
create_mailboxlist_mailboxesget_messagesread_messagedelete_mailbox
Migration map:
create_mailbox->create_signup_inboxget_messages+read_message->wait_for_verification_email+get_latest_email- multi-step signup orchestration ->
complete_signup_flow
Directory listing assets
Prepared listing payloads are in /directory-listings for:
- modelcontextprotocol/servers
- mcp.so
- awesome-mcp
Public endpoint deployment
Deployment templates for https://uncorreotemporal.com/mcp are in /deploy.
Development
uv run pytest
uv run uncorreotemporal-mcp
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。