Famulor▌

by bekservice
Famulor — Voice agent platform for automated phone calls: configure assistants, manage campaigns, send SMS, and run mid-
Voice agent platform for phone calling, assistant configuration, campaign management, SMS messaging, and mid-call tool execution for automated voice interactions.
github stars
★ 1
best for
- / Sales teams automating outbound calls
- / Customer support with AI voice agents
- / Developers building voice interaction workflows
- / Businesses running phone campaigns
capabilities
- / Make AI-powered phone calls
- / Manage voice assistants and configurations
- / Retrieve call transcripts and recordings
- / Configure call campaigns
- / Send SMS messages
- / Execute tools during active calls
what it does
Voice agent platform that enables AI-powered phone calls through ChatGPT and other MCP clients. Make calls, manage voice assistants, and retrieve call transcripts and recordings.
about
Famulor is a community-built MCP server published by bekservice that provides AI assistants with tools and capabilities via the Model Context Protocol. Famulor — Voice agent platform for automated phone calls: configure assistants, manage campaigns, send SMS, and run mid- It is categorized under communication, developer tools.
how to install
You can install Famulor in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server supports remote connections over HTTP, so no local installation is required.
license
NOASSERTION
Famulor is released under the NOASSERTION license.
readme
🤖 Famulor MCP Server
An MCP (Model Context Protocol) server for the Famulor Voice Agent Platform that enables AI-powered phone calls, assistant management, and call data retrieval through ChatGPT and other MCP-compatible clients.

Demo Video
https://www.youtube.com/watch?v=OMQeTiBNW3Q
Overview
This MCP server provides access to the Famulor Voice Agent Platform, allowing users to make AI-powered phone calls, manage voice assistants, and retrieve call transcripts and recordings - all directly from any MCP-compatible client like ChatGPT Desktop, Claude Desktop, or other MCP-compatible applications.
🌐 Online MCP Server
You can use the hosted MCP server without local installation:
- Server URL: https://mcp.famulor.io
- SSE Endpoint: https://mcp.famulor.io/sse
- Health Check: https://mcp.famulor.io/health
The server is ready to use! For online usage instructions, see the Online Deployment Guide.
Features
- 📞 Make Calls - Initiate AI-powered phone conversations
- 🤖 Manage Assistants - Get and manage your AI assistants
- 📊 Retrieve Call Data - Get transcripts, recordings, and metadata
- 🔒 Secure Authentication - API key-based authentication per user
Prerequisites
- An MCP-compatible client such as:
- A Famulor API key (Get one here)
Note: If you want to run your own local server (Option 2), you'll also need:
- Node.js >= 20.0.0 (Download)
Quick Start
Option 1: Use Online MCP Server (Recommended - No Installation Required)
The easiest way to get started! Use our hosted MCP server at https://mcp.famulor.io.
1. Get Your API Key
- Go to Famulor API Keys
- Sign in or create an account
- Create a new API key
- Copy the API key (you'll need it in the next step)
2. Configure MCP in Your Client
See the Client-Specific Installation section below for detailed instructions for your MCP client (Cursor, Claude Desktop, ChatGPT Desktop, etc.).
Quick Example Configuration:
{
"mcpServers": {
"famulor": {
"url": "https://mcp.famulor.io/sse",
"env": {
"FAMULOR_API_KEY": "your-api-key-here"
}
}
}
}
3. Restart Your MCP Client
- Close your MCP client completely
- Restart it
- The MCP server should be automatically connected
4. Test It!
In your MCP client (ChatGPT, Claude, etc.), try asking:
- "Show me my Famulor assistants"
- "List my recent calls"
- "Make a call with assistant [ID] to [phone number]"
Option 2: Use Your Own Local Server
If you prefer to run the server locally:
1. Clone the Repository
git clone https://github.com/bekservice/Famulor-MCP.git
cd Famulor-MCP
2. Install Dependencies
npm install
3. Build the Server
npm run build
4. Get Your API Key
- Go to Famulor API Keys
- Sign in or create an account
- Create a new API key
- Copy the API key (you'll need it in the next step)
5. Configure MCP in Your Client
Create or edit the MCP configuration file for your platform and client. See the Client-Specific Installation section below for detailed instructions.
Example Configuration:
{
"mcpServers": {
"famulor": {
"command": "node",
"args": [
"/absolute/path/to/Famulor-MCP/dist/index.js"
],
"env": {
"FAMULOR_API_KEY": "your-api-key-here"
}
}
}
}
Important:
- Replace
/absolute/path/to/Famulor-MCPwith the actual absolute path to your cloned repository - Replace
your-api-key-herewith your actual Famulor API key - On Windows, use forward slashes or escaped backslashes in the path
Example paths:
- macOS:
/Users/username/Famulor-MCP/dist/index.js - Windows:
C:/Users/username/Famulor-MCP/dist/index.jsorC:\Users\username\Famulor-MCP\dist\index.js - Linux:
/home/username/Famulor-MCP/dist/index.js
6. Restart Your MCP Client
- Close your MCP client (ChatGPT Desktop, Claude Desktop, etc.) completely
- Restart it
- The MCP server should be automatically connected
7. Test It!
In your MCP client (ChatGPT, Claude, etc.), try asking:
- "Show me my Famulor assistants"
- "List my recent calls"
- "Make a call with assistant [ID] to [phone number]"
Client-Specific Installation
Choose your MCP client below for specific installation instructions:
For Claude Desktop
Important: Claude Desktop currently only supports local command-based MCP server configurations. HTTP/URL-based configurations are not supported, even in the latest version.
Setup Instructions
-
Find your configuration file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
- macOS:
-
Add the MCP server configuration:
Open the configuration file and add the following to the
mcpServerssection:{ "mcpServers": { "famulor": { "command": "node", "args": [ "/absolute/path/to/Famulor-MCP/dist/index.js" ], "env": { "FAMULOR_API_KEY": "your-api-key-here" } } } }Important:
- Replace
/absolute/path/to/Famulor-MCPwith your actual absolute path to the repository - Replace
your-api-key-herewith your actual Famulor API key - You can get your API key at Famulor API Keys
- Make sure you've built the server:
npm run build - The path must be absolute (not relative)
- Replace
-
Restart Claude Desktop completely for the changes to take effect.
For Cursor
Option 1: Use Online MCP Server (Recommended - No Installation Required)
Global Installation (Recommended):
-
Go to Cursor Settings > Tools & Integrations
-
Click "New MCP Server"
-
This will open
~/.cursor/mcp.json -
Add the following configuration:
{ "mcpServers": { "famulor": { "type": "http", "url": "https://mcp.famulor.io/sse", "headers": { "Authorization": "Bearer your-api-key-here" } } } }Important:
- Replace
your-api-key-herewith your actual Famulor API key - The API key must be prefixed with
Bearerin the Authorization header - You can get your API key at Famulor API Keys
- Replace
-
Go back to Settings > MCP and click the refresh button
-
The Cursor agent will now be able to use the Famulor MCP tools
Project-Specific Installation:
- Create or edit
.cursor/mcp.jsonin your project root - Add the same configuration as above
- Restart Cursor or refresh MCP settings
Option 2: Use Your Own Local Server
Global Installation (Recommended):
-
Go to Cursor Settings > Tools & Integrations
-
Click "New MCP Server"
-
This will open
~/.cursor/mcp.json -
Add the following configuration:
{ "mcpServers": { "famulor": { "command": "node", "args": [ "/absolute/path/to/Famulor-MCP/dist/index.js" ], "env": { "FAMULOR_API_KEY": "your-api-key-here" } } } } -
Go back to Settings > MCP and click the refresh button
-
The Cursor agent will now be able to use the Famulor MCP tools
Project-Specific Installation:
- Create or edit
.cursor/mcp.jsonin your project root - Add the same configuration as above
- Restart Cursor or refresh MCP settings
For Claude Code
Option 1: Use Online MCP Server (Recommended - No Installation Required)
To add the online MCP server to Claude Code, run this command in your terminal:
claude mcp add-json "famulor" '{"type":"http","url":"https://mcp.famulor.io/sse","headers":{"Authorization":"Bearer your-api-key-here"}}'
Note:
- Replace
your-api-key-herewith your actual Famulor API key - The API key must be prefixed with
Bearerin the Authorization header - You can get your API key at Famulor API Keys
Option 2: Use Your Own Local Server
To add your local MCP server to Claude Code, run this command in your terminal:
claude mcp add-json "famulor" '{"command":"node","args":["/absolute/path/to/Famulor-MCP/dist/index.js"],"env":{"FAMULOR_API_KEY":"your-api-key-here"}}'
Note: Replace /absolute/path/to/Famulor-MCP/dist/index.js with your actual path and your-api-key-here with your actual API key.
See the official Claude Code MCP documentation for more details.
For ChatGPT Desktop App
Option 1: Use Online MCP Server (Recommended - No Installation Required)
- Find your configuration file:
- macOS:
~/Library/Application Support/ChatGPT/mcp.json - Windows:
%APPDATA%\ChatGPT\mcp.jsonorC:\Users\YourUsername\AppData\Roaming\ChatGPT\mcp.json - Linux: `~/.config/ChatGPT/
- macOS: