How to Use the Vapi MCP in Vercel AI SDK

Q: How do I check recent conversations using Vapi and the Vercel AI SDK?

Simply call listcalls. This returns a list of all active or completed voice sessions. You can then grab specifics for any session ID, pulling transcripts directly into your UI.

Q: Does the MCP Server support multiple agent roles with Vercel AI SDK?

Yes. The listagenttools function shows every tool available to Vapi assistants. This means you can control exactly what actions an assistant can take during a session.

Q: Can I list all available numbers to use Vapi and the Vercel AI SDK?

Absolutely. Call listphonenumbers to get a complete inventory of every number connected to your Vapi account before starting any call.

Stream Voice AI results directly into your UI with Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Vapi MCP to Vercel AI SDK

Create your Vinkius account to connect Vapi to Vercel AI SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Vapi with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build real-time voice features with the MCP Server

Your agent uses Vapi to manage calls and transcribe audio. You can call `list_calls` to fetch a list of recent sessions, then use `get_call_details` to pull transcripts and metrics for display in your component. Because the results stream directly into Next.js or React, users see data appear instantly—no loading spinners needed. It just works live.

Configure voice assistants with Vercel AI SDK

Need a new persona? You use `create_assistant` to set up the core configuration for your Voice AI assistant, specifying the model, transcribing service, and voice. This tool ensures the agent behaves exactly how you want it to. The updated settings can be managed later using `update_assistant`, letting you tweak roles or voices without redeploying anything.

Initiate calls from your front end

You don't have to build the phone logic yourself. Use `create_phone_call` when a user needs immediate support, passing in the required number ID and customer details. This tool handles the complex setup for an outbound call. For web interactions, generating a dedicated link is simple with `create_web_call`, giving your users a ready-to-use endpoint.

Setup guide

Set up Vapi MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Vapi tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Vapi transactions",
});

console.log(text);
await mcpClient.close();

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Vapi. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Vapi now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Vapi MCP in Vercel AI SDK

Simply call `list_calls`. This returns a list of all active or completed voice sessions. You can then grab specifics for any session ID, pulling transcripts directly into your UI.

Yes. The `list_agent_tools` function shows every tool available to Vapi assistants. This means you can control exactly what actions an assistant can take during a session.

This server primarily touches call metadata, including transcripts and specific customer details passed through `create_phone_call`. Always handle this PII with care.

Absolutely. Call `list_phone_numbers` to get a complete inventory of every number connected to your Vapi account before starting any call.

Yes, it’s built for that environment. You can stream all tool results directly into your client-side code using TypeScript SDK, making it perfect for Edge Functions.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript