How to Use the Aircall MCP in Vercel AI SDK

Q: How do I connect the Vercel AI SDK to Aircall?

Pass the Vinkius endpoint URL into createMCPClient({ transport: { type: "http", url: "..." } }). Then feed mcpClient.tools() into your generation function.

Q: Can I stream Aircall logs into a Vercel AI SDK application?

Yes. When the agent triggers listcalls, the framework streams those JSON results back to the client. Your React component renders the call history row by row as the data arrives.

Q: How do I search for a specific phone number?

Your agent uses the searchcontacts tool to find exact matches. Provide the phone number in the prompt, and the AI will pull the corresponding Aircall contact record.

Stream live Aircall contact data and call logs straight into your Next.js frontend using the 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 Aircall MCP to Vercel AI SDK

Create your Vinkius account to connect Aircall 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 Aircall with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build live call dashboards with Vercel AI SDK

Connect this Aircall MCP Server directly to your `generateText` calls to pull real-time phone system data without making users stare at loading spinners. The moment your agent pulls data via `list_calls`, those records stream straight into your UI components. Building a custom support interface gets much easier when you map `get_user_details` to a live availability widget. You pass the Vinkius HTTP endpoint into your MCP setup, and your application instantly knows exactly which team members are free to take a call.

Stream contact creation directly from chat

Wire the `create_contact` tool into your chat interface so your agent can save customer details mid-conversation. Users hate switching tabs to log a new phone number. The Vercel AI SDK handles the MCP execution while the person typing sees the confirmation render instantly. When someone asks for a specific customer record, your agent fires `search_contacts` and streams the matching phone numbers back. You just call `mcpClient.close()` when the session ends, keeping your Edge Functions clean and memory leaks out of your production environment.

Expose team routing logic to end users

Expose `list_teams` and `list_numbers` through your Svelte or Vue frontend to give users a transparent view of your phone configuration. Let your customers see exactly how their calls get routed before they even dial. If a call drops, the user can ask your agent what happened. The AI hits `get_call_details` to grab the technical logs and streams the exact error reason back to the browser. No more waiting on support tickets to debug a bad connection.

Setup guide

Set up Aircall 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 Aircall 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 Aircall 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 Aircall. 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 Aircall 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 Aircall MCP in Vercel AI SDK

Pass the Vinkius endpoint URL into `createMCPClient({ transport: { type: "http", url: "..." } })`. Then feed `mcpClient.tools()` into your generation function.

Yes. When the agent triggers `list_calls`, the framework streams those JSON results back to the client. Your React component renders the call history row by row as the data arrives.

It runs perfectly on the edge. The MCP setup uses standard HTTP transports, meaning you avoid the cold boot penalties of heavy Node.js libraries when querying Aircall availability.

Your agent uses the `search_contacts` tool to find exact matches. Provide the phone number in the prompt, and the AI will pull the corresponding Aircall contact record.

Vinkius isolates every MCP session inside a V8 sandbox that gets destroyed immediately after your request finishes. Your customer phone numbers, call logs, and team availability metadata never touch persistent storage.

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