mcp-server

The Vapi Model Context Protocol server allows you to integrate with Vapi APIs through function calling.

1. Open Claude Desktop and press CMD + , to go to Settings.
2. Click on the Developer tab.
3. Click on the Edit Config button.
4. This will open the claude_desktop_config.json file in your file explorer.
5. Get your Vapi API key from the Vapi dashboard (https://dashboard.vapi.ai/org/api-keys).
6. Add the following to your claude_desktop_config.json file. See here for more details.
7. Restart the Claude Desktop after editing the config file.

{
  "mcpServers": {
    "vapi-mcp-server": {
      "command": "npx",
      "args": [
          "-y",
          "@vapi-ai/mcp-server"
      ],
      "env": {
        "VAPI_TOKEN": "<your_vapi_token>"
      }
    }
  }
}

1. Create or import a phone number using the Vapi dashboard (https://dashboard.vapi.ai/phone-numbers).
2. Create a new assistant using the existing 'Appointment Scheduler' template in the Vapi dashboard (https://dashboard.vapi.ai/assistants).
3. Make sure to configure Claude Desktop to use the Vapi MCP server and restart the Claude Desktop app.
4. Ask Claude to initiate or schedule a call. See examples below:

Example 1: Request an immediate call

I'd like to speak with my ShopHelper assistant to talk about my recent order. Can you have it call me at +1234567890?

Example 2: Schedule a future call

I need to schedule a call with Mary assistant for next Tuesday at 3:00 PM. My phone number is +1555123456.

To connect to Vapi's MCP server via Server-Sent Events (SSE) Transport:

• Connect to https://mcp.vapi.ai/sse from any MCP client using SSE Transport
• Include your Vapi API key as a bearer token in the request headers
• Example header: Authorization: Bearer your_vapi_api_key_here

This connection allows you to access Vapi's functionality remotely without running a local server.

# Install dependencies
npm install

# Build the server
npm run build

Update your claude_desktop_config.json to use the local server.

{
  "mcpServers": {
    "vapi-local": {
      "command": "node",
      "args": [
        "<path_to_vapi_mcp_server>/dist/index.js"
      ],
      "env": {
        "VAPI_TOKEN": "<your_vapi_token>"
      }
    },
  }
}

The project has two types of tests:

Unit tests use mocks to test the MCP server without making actual API calls to Vapi.

# Run unit tests
npm run test:unit

E2E tests run the full MCP server with actual API calls to Vapi.

# Set your Vapi API token
export VAPI_TOKEN=your_token_here

# Run E2E tests
npm run test:e2e

Note: E2E tests require a valid Vapi API token to be set in the environment.

To run all tests at once:

npm test

• VAPI Remote MCP Server
• VAPI MCP Tool
• Model Context Protocol
• Claude Desktop

The Vapi MCP Server provides the following tools for integration:

• list_assistants: Lists all Vapi assistants
• create_assistant: Creates a new Vapi assistant
• update_assistant: Updates an existing Vapi assistant
• get_assistant: Gets a Vapi assistant by ID

• list_calls: Lists all Vapi calls
• create_call: Creates an outbound call
• get_call: Gets details of a specific call

Note: The create_call action supports scheduling calls for immediate execution or for a future time.

• list_phone_numbers: Lists all Vapi phone numbers
• get_phone_number: Gets details of a specific phone number

• list_tools: Lists all Vapi tools
• get_tool: Gets details of a specific tool