How to Use the Callpicker MCP in Vercel AI SDK

Q: How do I use the Callpicker MCP with the Vercel AI SDK to show call logs?

First, instantiate the client with createMCPClient using your Vinkius URL. Then, pass the Callpicker tools to streamText and render the streaming data inside your React components. The AI SDK handles the rest.

Q: Can my agent make calls using Callpicker and the Vercel AI SDK?

Yes. The makecall tool lets your agent initiate a phone call on your behalf. You can connect this to a button or command in your UI to dial any number.

Q: Is it possible to get a call recording URL with Callpicker and the Vercel AI SDK?

Absolutely. Just ask your agent to use the getrecordingurl tool with a specific call ID. The URL will be returned as part of the streaming response, ready to be used in your application.

Q: What kind of reports can I generate with this MCP?

You can pull raw data for custom reporting. The getcdrreport tool gives you access to the Call Detail Records, which you can then process and visualize however you need to in your frontend application.

Build UIs that show live Callpicker data. With the Vercel AI SDK, call logs and statuses stream right into your React components.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Callpicker MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Live Call Dashboards

Stop building dashboards that rely on a refresh button. With the Vercel AI SDK, you can build a UI where call activity appears the moment it happens. Your agent can use `list_call_logs` and `get_pbx_system_status` to feed a real-time monitoring component in your Next.js or React application. When a user wants to investigate a specific call, your agent can use `get_call_details` and `get_recording_url`. The data streams directly into the UI, so the user sees details populating one by one instead of staring at a loading spinner. It’s a much better user experience, and it’s built right into the SDK.

Trigger Calls Directly from Your UI

Let users take action without leaving your app. The `make_call` tool gives your agent the ability to initiate a phone call from any number you provide. You can wire this up to a button in your sales dashboard or customer support panel. This creates a complete interactive loop. A user can click to dial, and once the call is over, your agent can immediately fetch the new entry with `list_call_logs` and display it in the history. The whole interaction feels instant because the data is streaming.

Inspect PBX State with the Vercel AI SDK

Your agent can query the PBX system directly through this MCP Server. Use the `list_pbx_extensions` and `list_virtual_numbers` tools to populate dropdowns or tables in your application's admin panel. It's a simple way to give admins visibility into the phone system's configuration. Because the Vercel AI SDK streams results, the user sees the list of extensions build in real-time. It feels responsive, not like a typical API call that waits for the whole list. This is a big deal for UIs with lots of data, and a unique feature of how this MCP works with the SDK.

Setup guide

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

First, instantiate the client with `createMCPClient` using your Vinkius URL. Then, pass the Callpicker tools to `streamText` and render the streaming data inside your React components. The AI SDK handles the rest.

Yes. The `make_call` tool lets your agent initiate a phone call on your behalf. You can connect this to a button or command in your UI to dial any number.

Absolutely. Just ask your agent to use the `get_recording_url` tool with a specific call ID. The URL will be returned as part of the streaming response, ready to be used in your application.

You can pull raw data for custom reporting. The `get_cdr_report` tool gives you access to the Call Detail Records, which you can then process and visualize however you need to in your frontend application.

Callpicker only processes call metadata and recording URLs, not the raw audio. All communication with this MCP server is over an encrypted HTTPS connection, and your Vinkius token is the only credential needed for authentication. The data is ephemeral on the server.

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