What is the Vapi MCP server?

The Vapi MCP server is a bridge that integrates Vapi’s voice AI capabilities with the Cursor code editor using the Model Context Protocol (MCP).

What is MCP?

MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to LLMs, allowing AI models to interact with external data and tools.

What are the key features of the Vapi MCP server?

Key features include seamless integration with Cursor, MCP compliance, a modular architecture, secure communication, and a comprehensive toolset for managing voice assistants and calls.

What use cases does the Vapi MCP server enable?

It enables voice-controlled code editing, AI-powered debugging, voice-activated command execution, AI assistant integration, and hands-free navigation within Cursor.

How do I set up the Vapi MCP server?

The setup involves configuring environment variables, building the server using npm install and npm run build, and configuring Cursor with the correct paths and API keys in the MCP settings.

What environment variables are required for the Vapi MCP server?

The required environment variables are VAPI_ORG_ID, VAPI_PRIVATE_KEY, VAPI_KNOWLEDGE_ID, VAPI_JWT_PRIVATE, and NODE_ENV.

What should I do if I get a “Client Closed” error in Cursor?

Ensure the cwd parameter is set correctly in the MCP configuration, all required environment variables are passed, and the package.json includes "type": "module".

What should I do if I get a “Module Not Found” error?

Check that you are running the server from the correct directory, rebuild the project with npm run build, and ensure all dependencies are installed with npm install.

What tools are available with the Vapi MCP server?

The available tools are vapi_call (make outbound calls), vapi_assistant (manage voice assistants), and vapi_conversation (retrieve conversation details).

What is UBOS?

UBOS is a full-stack AI Agent Development Platform designed to help businesses integrate AI Agents into various departments, orchestrate them, connect them with enterprise data, and build custom AI Agents using their own LLM models.