- Explore MCP Servers
- SendPhoneCallMCP
Sendphonecallmcp
What is Sendphonecallmcp
SendPhoneCallMCP is a Model Control Protocol server that enables users and agents to make AI-powered phone calls through a simple API interface.
Use cases
Use cases include making appointment reminders, conducting surveys, providing customer support, and sending alerts or notifications to users.
How to use
To use SendPhoneCallMCP, set up a Supabase account, configure environment variables, and run the server. You can then access various API endpoints to manage phone calls and user preferences.
Key features
Key features include the ability to initiate phone calls, manage call history, update user preferences, and select AI model and voice options for calls.
Where to use
SendPhoneCallMCP can be used in customer service, telemarketing, automated notifications, and any application requiring automated phone interactions.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Overview
What is Sendphonecallmcp
SendPhoneCallMCP is a Model Control Protocol server that enables users and agents to make AI-powered phone calls through a simple API interface.
Use cases
Use cases include making appointment reminders, conducting surveys, providing customer support, and sending alerts or notifications to users.
How to use
To use SendPhoneCallMCP, set up a Supabase account, configure environment variables, and run the server. You can then access various API endpoints to manage phone calls and user preferences.
Key features
Key features include the ability to initiate phone calls, manage call history, update user preferences, and select AI model and voice options for calls.
Where to use
SendPhoneCallMCP can be used in customer service, telemarketing, automated notifications, and any application requiring automated phone interactions.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Content
SendPhoneCall MCP Server
This repository contains the MCP (Model Control Protocol) server implementation for the SendPhoneCall service, which enables AI-powered phone calls.
Prerequisites
- Node.js (v14 or higher)
- Supabase account and project
- Environment variables set up (see below)
Environment Variables
Create a .env file in the root directory with the following variables:
PORT=3040 NODE_ENV=development SUPABASE_URL=your_supabase_url SUPABASE_KEY=your_supabase_service_key BYPASS_MCP_AUTH=true # Only for development
Database Setup
- Create a Supabase project if you haven’t already
- Execute the SQL in
supabase-setup.sqlin the Supabase SQL Editor to create the necessary functions - Run the database setup script:
node setup-database.js
This will create the following tables:
user_settings: Stores user preferences for phone callscall_history: Records history of phone calls madecredits: Manages user credit balance for making calls
Starting the Server
node server.js
For development with authentication bypass:
NODE_ENV=development BYPASS_MCP_AUTH=true node server.js
API Endpoints
Health Check
GET /health
MCP API
POST /api/v1/mcp
Available Tools
The MCP server provides the following tools:
getModelOptions
Returns available AI model options for phone calls.
getVoiceOptions
Returns available voice options for phone calls.
updateCallPreferences
Updates a user’s default preferences for phone calls.
Parameters:
defaultVoice: Default voice to use (string)defaultModel: Default AI model to use (string)defaultTemperature: Default temperature setting (0.0-1.0)defaultFromNumber: Default phone number to make calls from (E.164 format)defaultVoicemailAction: Action to take when voicemail is detected (leave_message, hang_up, retry_later)
makePhoneCall
Initiates a phone call.
Parameters:
toNumber: Phone number to call (E.164 format)fromNumber: Phone number to call from (E.164 format)voiceId: Voice to usemodelId: AI model to usetemperature: Temperature setting (0.0-1.0)instructions: Instructions for the AI
Testing the API
Initialize a session:
curl -X POST http://localhost:3040/api/v1/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","method":"initialize","params":{"clientName":"test-client","clientVersion":"1.0.0"},"id":1}'
Execute a tool (example: getModelOptions):
curl -X POST http://localhost:3040/api/v1/mcp \
-H "Content-Type: application/json" \
-H "Authorization: Bearer SESSION_ID" \
-d '{"jsonrpc":"2.0","method":"tools/execute","params":{"name":"getModelOptions","arguments":{}},"id":2}'
Implementation Plan Progress
See mcp-implementation-plan-progress.md for the current status of the implementation plan.
Dev Tools Supporting MCP
The following are the main code editors that support the Model Context Protocol. Click the link to visit the official website for more information.










