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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
E2B
Using MCP to run code via e2b.