asterisk-voice-mcp
Enables AI agents to place VoIP phone calls via Asterisk, play TTS messages, capture DTMF input, and optionally record and transcribe voice responses.
README
Asterisk Voice MCP Server
A self-hosted Model Context Protocol (MCP) server that lets an AI agent place VoIP phone calls via Asterisk, play TTS messages, capture DTMF input, and optionally record voice responses to be transcribed.
Architecture
graph TD
Agent[AI Agent (Claude/Hermes)] -->|MCP over stdio| MCPServer[MCP Server (Python)]
MCPServer -->|ARI HTTP/WebSocket| Asterisk[Asterisk PBX (Docker)]
Asterisk -->|SIP/RTP| Softphone[Linphone Softphone]
MCPServer -->|TTS API / STT API| Speechmatics[Speechmatics API]
Features
- Place Calls: Initiate calls to a SIP endpoint.
- TTS: Play dynamically generated speech.
- DTMF Capture: Prompt the user for keypad input.
- Voice Capture & STT: Record user audio and transcribe it via Speechmatics.
- Tool integration: Fully compliant MCP server that exposes tools
place_call,send_dtmf,hangup_call,health_check.
Prerequisites
- Docker & Docker Compose
- Python 3.11+
- Linphone app
- Speechmatics API Key (optional, defaults to mock if absent)
Setup
- Clone the repository (or navigate to directory).
- Configure environment variables:
cp .env.example .env # Edit .env and provide your SPEECHMATICS_API_KEY if desired. - Start Asterisk:
docker compose up -d - Register Linphone:
- SIP Server: your host IP or domain
- Port: 5060 (UDP/TCP)
- Username:
linphone-user - Password: the value of
SIP_PASSWORDfrom your.env(generated at deploy time; see setup.sh)
Usage
Start the MCP server to expose tools:
python src/mcp_server.py
Example MCP Client Configuration
See config/mcp.json for an example of how to configure an MCP client (like Claude Desktop) to use this server.
Testing without a phone
Run the self-test script, which spins up a mock PJSIP endpoint and runs an end-to-end call test using a local bot.
python scripts/self_test.py
Security Notes
- Never expose ARI/SIP to the public internet without proper authentication, firewalls, and Fail2Ban.
- Secrets should remain in
.env. - Use strong endpoint secrets for SIP registrations.
- Lock down RTP ports.
License
MIT License
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
E2B
Using MCP to run code via e2b.
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.