Vapi MCP for Cursor

What is Vapi MCP for Cursor?

Vapi MCP for Cursor is a Model Context Protocol (MCP) server that integrates Vapi's voice AI capabilities with the Cursor editor, allowing users to manage Vapi voice assistants, make outbound calls, and retrieve conversation details directly from Cursor.

How to use Vapi MCP for Cursor?

Configure the server in Cursor's .cursor/mcp.json file with the required environment variables and working directory. Build the server with npm install && npm run build inside the vapi-mcp-server directory, then set the command to node, type to stdio, and provide the absolute path to dist/index.js along with the cwd parameter.

Key features of Vapi MCP for Cursor

• Make outbound calls using Vapi's voice AI
• Manage voice assistants (create, get, list, update, delete)
• Retrieve conversation details from calls
• Integrates directly with Cursor's MCP framework
• Uses stdio transport for seamless communication

Use cases of Vapi MCP for Cursor

• Automate outbound voice calls from within your development environment
• Create and manage Vapi voice assistants without leaving Cursor
• Fetch call logs and conversation data for analysis or debugging
• Streamline voice AI workflows by controlling Vapi through Cursor's MCP tools

FAQ from Vapi MCP for Cursor

What environment variables are required?

The server requires VAPI_ORG_ID, VAPI_PRIVATE_KEY, VAPI_KNOWLEDGE_ID, VAPI_JWT_PRIVATE, and NODE_ENV (set to development).

How do I fix a "Client Closed" error in Cursor?

Ensure the cwd parameter is set correctly, all environment variables are passed in the MCP configuration, package.json has "type": "module", and the dist/index.js file is executable. Test the server manually with node --trace-warnings dist/index.js.

What transport type does this server use?

The server uses the stdio transport type for proper integration with Cursor.

Where does the server need to be run from?

The server must be run from the vapi-mcp/vapi-mcp-server directory, and the cwd parameter in the MCP configuration must point to that directory.

What are the known module-related issues?

If "Cannot find module" errors occur, check that the working directory is correct, rebuild with npm run build, and ensure all dependencies are installed with npm install.