Vapi

v0.0.9Communicationstable

Enables integration with Vapi's voice AI platform to manage assistants, create and schedule phone calls with dynamic variables, and manage phone numbers through function calling.

aimcpmcp-servervapivoice-agents
Share:
51
Stars
0
Downloads
0
Weekly
0/5

What is Vapi?

Vapi is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables integration with vapi's voice ai platform to manage assistants, create and schedule phone calls with dynamic variables, and manage phone numbers through function calling.

Enables integration with Vapi's voice AI platform to manage assistants, create and schedule phone calls with dynamic variables, and manage phone numbers through function calling.

This server falls under the Communication category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Enables integration with Vapi's voice AI platform to manage

Use Cases

Voice AI assistant management
Phone call automation and scheduling
VapiAI

Maintainer

LicenseMIT License
Languagetypescript
Versionv0.0.9
UpdatedMay 19, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

NPM

npx -y @vapi-ai/mcp-server

Manual Installation

npx -y @vapi-ai/mcp-server

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Vapi

The Vapi MCP Server integrates AI assistants directly with Vapi's voice AI platform, enabling creation and management of voice assistants, initiation of outbound phone calls (immediate or scheduled), and management of phone numbers — all through natural language or tool calls. It supports dynamic prompt variables so calls can be personalised at the moment of dispatch, and exposes the full Vapi assistant lifecycle including create, update, list, and delete operations. Whether you want to automate appointment reminders, build a voice-based customer support flow, or programmatically manage a fleet of AI phone agents, this server makes those workflows accessible from any MCP-compatible client.

Prerequisites

  • A Vapi account and API token from dashboard.vapi.ai
  • Node.js 18+ and npx available in your terminal
  • Claude Desktop, Claude Code CLI, or another MCP-compatible client
  • A configured Vapi assistant and phone number (set up in the Vapi dashboard before making calls)
  • Target phone numbers in E.164 format (e.g. +1234567890) for outbound call testing
1

Get your Vapi API token

Log in to dashboard.vapi.ai, navigate to Account > API Keys, and create or copy your API token. Store it securely — you will pass it as the VAPI_TOKEN environment variable.

2

Add the server via Claude Code CLI (recommended)

If you use Claude Code, the easiest way to add the server is with the `claude mcp add` command, which handles registration automatically.

claude mcp add vapi -- npx -y @vapi-ai/mcp-server
3

Or add the server to Claude Desktop manually

Edit your claude_desktop_config.json to register the Vapi MCP server. Replace the VAPI_TOKEN value with your actual token.

{
  "mcpServers": {
    "vapi": {
      "command": "npx",
      "args": ["-y", "@vapi-ai/mcp-server"],
      "env": {
        "VAPI_TOKEN": "your-vapi-api-token-here"
      }
    }
  }
}
4

Restart your MCP client

Fully quit and relaunch Claude Desktop or reload your MCP configuration. The Vapi tools for assistant management, call operations, and phone number management should now appear.

5

Create your first voice assistant

In a new conversation, ask Claude to list your existing Vapi assistants or create a new one to verify the integration is working.

6

Make a test outbound call

Once you have a Vapi assistant set up, ask Claude to initiate a call using that assistant to a test phone number.

Vapi Examples

Client configuration

Complete claude_desktop_config.json block for the Vapi MCP Server with API token authentication.

{
  "mcpServers": {
    "vapi": {
      "command": "npx",
      "args": ["-y", "@vapi-ai/mcp-server"],
      "env": {
        "VAPI_TOKEN": "your-vapi-api-token-here"
      }
    }
  }
}

Prompts to try

Example prompts for managing voice assistants, placing calls, and handling phone numbers via Vapi.

- "List all my Vapi voice assistants and their current configurations."
- "Create a voice assistant that greets callers and collects their appointment preferences."
- "Call +1234567890 right now using my appointment-reminder assistant."
- "Schedule a call with my support assistant for next Tuesday at 3:00 PM to +1555123456."
- "Show me the call history for the past 7 days and summarise outcomes."
- "Update my sales assistant's system prompt to include today's promotion details."

Troubleshooting Vapi

Authentication error: 401 Unauthorized when calling Vapi tools

Verify VAPI_TOKEN is set correctly in the env block of your MCP config. Tokens are found in dashboard.vapi.ai under Account > API Keys. Ensure you are copying the full token string without extra whitespace.

Outbound calls fail or go to voicemail immediately

Confirm the target phone number is in E.164 format (+1XXXXXXXXXX for US numbers). Verify the assistant ID and phone number ID are correctly configured in your Vapi dashboard — the phone number must be provisioned and assigned to your account.

npx fails to find or install @vapi-ai/mcp-server

Run 'npx -y @vapi-ai/mcp-server' manually in a terminal to see the full error. If npm registry access is blocked, try installing globally first: 'npm install -g @vapi-ai/mcp-server', then update your config command to 'vapi-ai-mcp-server'.

Frequently Asked Questions about Vapi

What is Vapi?

Vapi is a Model Context Protocol (MCP) server that enables integration with vapi's voice ai platform to manage assistants, create and schedule phone calls with dynamic variables, and manage phone numbers through function calling. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Vapi?

Install via npm with the command: npx -y @vapi-ai/mcp-server. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with Vapi?

Vapi works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Vapi free to use?

Yes, Vapi is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Browse More Communication MCP Servers

Explore all communication servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "vapi-mcp-server": { "command": "npx", "args": ["-y", "@vapi-ai/mcp-server"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Vapi?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides