agentline-mcp
Gives AI agents phone numbers, email, SMS, and voice calls as MCP tools, enabling them to provision numbers, capture 2FA codes, send messages, and make calls.
README
<!-- mcp-name: io.github.jgottlieb84/agentline-mcp -->
Agentline MCP
Give your AI agent a phone number, email, SMS, and voice calls — as MCP tools.
Install once in Claude Desktop, Cursor, Zed, Windsurf, or any MCP client, and your agent can provision phone numbers, capture 2FA codes, send SMS, place AI voice calls, and send/receive email directly.
Install
# requires uv — https://docs.astral.sh/uv/
uvx agentline-mcp
Or with pip:
pip install agentline-mcp
agentline-mcp
Configure
Set your API key as an environment variable. Get one at agentline.co.
export AGENTLINE_API_KEY=ag_live_...
Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"agentline": {
"command": "uvx",
"args": ["agentline-mcp"],
"env": {
"AGENTLINE_API_KEY": "ag_live_..."
}
}
}
}
Cursor
~/.cursor/mcp.json:
{
"mcpServers": {
"agentline": {
"command": "uvx",
"args": ["agentline-mcp"],
"env": {
"AGENTLINE_API_KEY": "ag_live_..."
}
}
}
}
Zed
Add to ~/.config/zed/settings.json:
{
"context_servers": {
"agentline": {
"command": {
"path": "uvx",
"args": ["agentline-mcp"],
"env": { "AGENTLINE_API_KEY": "ag_live_..." }
}
}
}
}
Windsurf / Continue / any stdio MCP client
Use the same uvx agentline-mcp command and set AGENTLINE_API_KEY in the server's env. All major MCP clients share the same stdio launch pattern.
Tools exposed
Phone numbers
provision_number— get a phone number the agent can userelease_number— release when done (avoids monthly charges)list_numbers— list provisioned numbers
SMS
send_sms— send an outbound SMSwait_for_sms— long-poll for the next inbound SMS (with optional regex match)capture_code— the killer flow. Provision + wait for 2FA code + release, in one call
Voice
make_call— place an outbound AI voice call (non-blocking, returns call_id)get_call— status, transcript, summary for a callhangup_call— end an in-progress call
create_email_address— provision an emaillist_email_addresses— list provisioned addressesrelease_email_address— releasesend_email— send an outbound emailwait_for_email— long-poll for an inbound emailcapture_email_code— provision + wait for email-based verification code + release
Example prompts
"Sign me up for Substack using a throwaway phone number. Capture the 2FA code, paste it into the signup form, then release the number."
"Call +15551234567, pose as my assistant scheduling a dentist appointment for next Tuesday morning. Summarize the outcome when the call ends."
"Provision a new email address, start a free trial on example.com with it, and tell me the verification code that arrives."
Environment variables
| Var | Required | Default | Notes |
|---|---|---|---|
AGENTLINE_API_KEY |
yes | — | Starts with ag_live_ or ag_test_ |
AGENTLINE_BASE_URL |
no | https://api.agentline.dev |
Override for self-hosted / staging |
License
MIT
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。