Vapi MCP
Build and control voice AI agents through the Vapi API
Last verified: August 31, 2026
How to Install Vapi MCP
$npx -y @vapi-ai/mcp-serverRequires Claude Desktop, Cursor, Windsurf, or another MCP-compatible client.
About Vapi MCP
The Vapi MCP server connects agents to Vapi's voice AI platform via function calling, letting an assistant create and configure voice agents, place and manage calls, and work with call data without leaving the chat. It is a narrow, purpose-built server rather than a general-purpose one — useful if voice is part of your product, and irrelevant if it isn't. Pairs naturally with CRM and scheduling servers for building phone-based workflows.
Vapi MCP is a Voice & Audio MCP server designed for developers and AI power users. It enables extending AI assistants with real-world capabilities by exposing a structured set of tools over the Model Context Protocol. Key capabilities include standards-based mcp server interface, works with claude, gpt, gemini, and other mcp clients, tool discovery and structured outputs, and structured tool calls that work cleanly inside an LLM context. It integrates with Claude Desktop, Cursor, Windsurf, and any MCP-compatible client, and is best suited for developers and AI power users who need ai engineers wiring assistants into real tools.
Key Features
- voice
- telephony
- ai-agents
- api
- Standards-based MCP server interface
- Works with Claude, GPT, Gemini, and other MCP clients
Pricing
- Core MCP server
- Community support
- Works with any MCP client
- Everything in Free
- Higher usage limits
- Priority support
- Everything in Pro
- SLA & SSO
- Dedicated support
Tier details are indicative — visit the Vapi MCP website for current pricing.
Pros & Cons
Pros
- Drop-in support across MCP-compatible AI clients
- Reduces prompt boilerplate by exposing concrete tool calls
- Active community and ongoing updates
Cons
- Requires an MCP-capable client to use
- Initial setup can require configuration
- Capability surface depends on what the underlying service exposes
Best For
- AI engineers wiring assistants into real tools
- Teams adopting MCP as an integration standard
- Power users who want more than chat
Screenshots
Screenshots coming soon —
Submit yours →Our Take on Vapi MCP
A focused server that does one thing. If you are building phone-based agents it saves real time; if you are not, skip it.