
quickvoice_mcp
MCP Server for QuickVoice.app
Repository Info
About This Server
MCP Server for QuickVoice.app
Model Context Protocol (MCP) - This server can be integrated with AI applications to provide additional context and capabilities, enabling enhanced AI interactions and functionality.
Documentation
!Image
QuickVoice MCP
A MCP server to communicate with QuickVoice AI Voice agents.
🚀 Quickstart
- Get your QuickVoice API credentials (agent ID and API key)
- Set up Claude Desktop with QuickVoice MCP
- Start making AI phone calls with natural language prompts
QuickVoice.app Web Interface
Accessing the Dashboard
- Go to quickvoice.app and sign in with your credentials
- Navigate to the Dashboard to view your agent status, call history, and credit usage
- Access the Settings page to manage your API keys and agent configuration
Managing Your Agent
- Create/Edit Agent: Configure your agent's voice, behavior, and response patterns
- Conversation History: Review past calls and analyze conversation transcripts
- Analytics: Track call performance metrics and user engagement
Getting API Credentials
- Go to Settings > API
- Generate a new API key if you don't have one
- Copy your Agent ID and API Key to use with the MCP integration
📱 Using with Claude Desktop
Claude Desktop Setup
- Open Claude Desktop
- Go to Settings > Developer > Edit Config
- Add the following to your
claude_desktop_config.json:
{
"mcpServers": {
"QuickVoice": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"QUICKVOICE_AGENT_ID",
"-e",
"QUICKVOICE_API_KEY",
"rexanity/quickvoice-mcp"
],
"env": {
"QUICKVOICE_AGENT_ID": "your-agent-id",
"QUICKVOICE_API_KEY": "your-api-key"
}
}
}
}
Example Prompts
Try asking Claude:
- "Call 555-123-4567 and schedule an appointment for tomorrow at 2pm"
- "Call my customer to follow up on their order status"
- "Make a call to check if a restaurant has availability for dinner tonight"
- "Call this number and ask about their business hours"
⚠️ Note: Using QuickVoice will consume API credits based on your account's billing terms.
For detailed instructions on integrating QuickVoice with Claude Desktop, see CLAUDE_DESKTOP.md.
Installation Options
Docker (Recommended)
# Pull the Docker image
docker pull rexanity/quickvoice-mcp
# Run the container
docker run -e QUICKVOICE_AGENT_ID="your-agent-id" -e QUICKVOICE_API_KEY="your-api-key" rexanity/quickvoice-mcp
Using Pip
pip install -e .
python -m src.server
Available Features
- Initiate Call Tool: Make outbound calls using QuickVoice AI agents
- Calls a phone number with specific context and instructions
- Includes automatic retry logic for API calls
Configuration
You can configure your QuickVoice API credentials in one of the following ways:
1. Environment Variables
Set the following environment variables:
export QUICKVOICE_AGENT_ID="your-agent-id"
export QUICKVOICE_API_KEY="your-api-key"
export QUICKVOICE_API_ENDPOINT="http://your-api-endpoint" # Optional, defaults to http://localhost:8000
export LOG_LEVEL="INFO" # Optional, defaults to INFO
2. MCP Config File
Create an MCP config file by copying the example:
cp mcp_config.json.example ~/.config/mcp/config.json
Then update the values in the config file:
{
"mcpServers": {
"QuickVoice": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"QUICKVOICE_AGENT_ID",
"-e",
"QUICKVOICE_API_KEY",
"rexanity/quickvoice-mcp"
],
"env": {
"QUICKVOICE_AGENT_ID": "your-agent-id",
"QUICKVOICE_API_KEY": "your-api-key"
}
}
}
}
Usage Examples
Initiating a Call
response = initiate_call(
phone_number="1234567890",
context="Customer information and relevant details",
instruction="Ask about their dinner plans"
)
🔧 Development
Poetry Setup
# Install Poetry if you don't have it
curl -sSL https://install.python-poetry.org | python3 -
# Install dependencies
poetry install
# Activate the virtual environment
poetry shell
# Run the server in development mode
poetry run python -m src.server
Docker Development
# Build the development image locally
docker build -t quickvoice-mcp-dev --target development .
# Run with mounted source code for live reloading
docker run -v $(pwd):/app -e QUICKVOICE_AGENT_ID="your-agent-id" -e QUICKVOICE_API_KEY="your-api-key" -e QUICKVOICE_API_ENDPOINT="http://host.docker.internal:8000" quickvoice-mcp-dev
Note: While the
:latesttag is implied when no tag is specified, using explicit tags (like:devor:1.0.0) is recommended for production environments to ensure version stability.
🔍 Troubleshooting
Log Locations
- macOS:
~/Library/Logs/Claude/mcp-server-quickvoice.log - Windows:
%APPDATA%\Claude\logs\mcp-server-quickvoice.log
Common Issues
API Connection Errors
- Verify your API credentials are correct
- Check that your API endpoint is reachable from your environment
- For Docker: ensure
host.docker.internalis used for local development
Call Not Initiating
- Confirm the phone number format is correct (include country code if necessary)
- Ensure your QuickVoice account has sufficient credits
- Check the API response for specific error messages
Quick Start
Clone the repository
git clone https://github.com/rexanity/quickvoice_mcpInstall dependencies
cd quickvoice_mcp
npm installFollow the documentation
Check the repository's README.md file for specific installation and usage instructions.
Repository Details
Recommended MCP Servers
Discord MCP
Enable AI assistants to seamlessly interact with Discord servers, channels, and messages.
Knit MCP
Connect AI agents to 200+ SaaS applications and automate workflows.
Apify MCP Server
Deploy and interact with Apify actors for web scraping and data extraction.
BrowserStack MCP
BrowserStack MCP Server for automated testing across multiple browsers.
Zapier MCP
A Zapier server that provides automation capabilities for various apps.