Famulor
MCP Server for Famulor Voice Agent Platform - AI-powered phone calling and voice assistant management through ChatGPT, Claude, and other MCP-compatible clients
claude mcp add --transport stdio bekservice-famulor-mcp node /absolute/path/to/Famulor-MCP/dist/index.js \ --env FAMULOR_API_KEY="your-api-key-here"
How to use
Famulor MCP Server exposes Famulor's Voice Agent Platform capabilities to any MCP-compatible client. Through the server you can initiate AI-powered phone calls, manage your Famulor assistants, and retrieve transcripts, call recordings, and related metadata. To connect from your MCP client (such as ChatGPT Desktop, Claude Desktop, Cursor, or other MCP-enabled apps), provide the server's endpoint and your API key so the client can authenticate and query Famulor data. Common tasks include listing assistants, starting a call with a chosen assistant, and fetching call transcripts or recordings for a given session.
The typical workflow is: obtain a Famulor API key from the Famulor portal, configure your MCP client to point at the local or hosted Famulor MCP server with your API key injected as an environment variable, then use natural language prompts in your MCP client to manage assistants, place calls, and retrieve call data. If you run locally, ensure you point the client to your local server (via the configured mcpServers entry) and set FAMULOR_API_KEY. If you use the hosted server, you’ll typically configure the client to call the hosted SSE endpoint and pass your API key in the environment or request headers as required by the client.
How to install
Prerequisites:
- Node.js 20.0.0 or newer
- npm (comes with Node.js)
- Access to a Famulor API key
Option A: Run the server locally from source
-
Clone the repository git clone https://github.com/bekservice/Famulor-MCP.git cd Famulor-MCP
-
Install dependencies npm install
-
Build the server npm run build
-
Obtain your Famulor API key
- Go to Famulor API Keys and generate a key
- Copy the key for use in the MCP config
-
Configure MCP in your client Create or edit your MCP configuration to point to the local server, for example: { "mcpServers": { "famulor": { "command": "node", "args": [ "/absolute/path/to/Famulor-MCP/dist/index.js" ], "env": { "FAMULOR_API_KEY": "your-api-key-here" } } } } Replace "/absolute/path/to/Famulor-MCP" with the actual absolute path on your machine and insert your API key.
-
Start using Close and restart your MCP client so it reconnects to the new server configuration.
Option B: Use the hosted online MCP server
- No local installation required. Use the hosted server at https://mcp.famulor.io
- In your MCP client configuration, set the SSE URL to https://mcp.famulor.io/sse and provide your API key (FAMULOR_API_KEY) in the environment or request headers as dictated by the client.
- Restart the client and begin issuing commands to manage assistants and calls.
Additional notes
Tips and caveats:
- Always use an absolute path for local server configurations (as required by several MCP clients).
- Keep your Famulor API key secure; do not hard-code it in public repos or share it in logs.
- If you switch between online and local usage, ensure the appropriate endpoint (https://mcp.famulor.io/sse or your local dist/index.js) is configured in the MCP client.
- When building locally, npm run build outputs the runnable bundle at dist/index.js which is referenced in the MCP config.
- For Windows paths in the config, you may need to use escaped backslashes or forward slashes (e.g., C:/path/to/Famulor-MCP/dist/index.js).
- If you encounter connection issues, verify that the API key has the necessary permissions in Famulor and that the MCP client is able to reach the configured SSE endpoint.
- The server supports API-key-based authentication per user; manage keys in the Famulor portal and map them per client as needed.
Related MCP Servers
agentql
Model Context Protocol server that integrates AgentQL's data extraction capabilities.
Pare
Dev tools, optimized for agents. Structured, token-efficient MCP servers for git, test runners, npm, Docker, and more.
taskflow
A task management Model Context Protocol (MCP) server that helps AI assistants break down user requests into manageable tasks with subtasks, dependencies, and notes. Enforces a structured workflow with user approval steps.
shodan
Shodan MCP server for Claude, Cursor & VS Code. 20 tools for passive reconnaissance, CVE/CPE intelligence, DNS analysis, and device search. 4 tools work free without an API key. OSINT and vulnerability research from your IDE.
mcp-spotify-player
MCP server to manage Spotify from MCP clients
mongo
MCP server that provide tools to LLMs such as claude in cursor to interact with MongoDB