How to Use the Freshcaller MCP in Vercel AI SDK

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

Run npm install ai @ai-sdk/mcp. Then configure createMCPClient with the Vinkius endpoint. Pass the resulting tools directly into your streamText function to start pulling call data.

Q: Can the Vercel AI SDK stream Freshcaller metrics in real-time?

Yes. When the agent calls listaccountmetrics, the SDK streams the JSON response directly to your React components. The user watches the call queue numbers update live.

Stream live Freshcaller telecom metrics and call histories directly into your React frontends 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 Freshcaller MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Call Center Dashboards

`list_account_metrics` and `list_calls` fetch live queue data so your AI client can stream the current state of your phone system straight to a Next.js frontend. You don't make users wait for a loading spinner. The Vercel AI SDK pushes the raw call volume numbers and recent phone logs into the UI as fast as the API returns them. Building a supervisor view requires instant feedback. When an admin asks for the latest dropped calls, the agent pulls the data and renders the table rows sequentially. It feels instant because the data streams the moment the MCP connection opens.

Vercel AI SDK Agent Management

`list_agents` and `get_agent_details` let your React application display exactly who is currently answering phones. The agent pulls the roster and streams the status of each representative directly into your custom interface. You see who is busy, who is offline, and who is available without writing custom polling logic. Managing a shift becomes a fast text prompt. A floor manager types a request to check team availability, and the SDK instantly streams the response. The underlying tool execution happens on the MCP Server, while the frontend updates live.

On-Demand Call Recording Retrieval

`get_call_recording` and `get_call_details` grab specific audio links and metadata when your users need to audit a previous conversation. Instead of forcing support leads to navigate the standard portal, your app fetches the exact recording link and streams the audio player directly into the chat window. This eliminates context switching during quality assurance reviews. The reviewer asks for yesterday's escalated calls, and the UI populates with playable audio files. You get a custom QA tool built entirely around streaming data.

Setup guide

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

Run `npm install ai @ai-sdk/mcp`. Then configure `createMCPClient` with the Vinkius endpoint. Pass the resulting tools directly into your `streamText` function to start pulling call data.

Yes. When the agent calls `list_account_metrics`, the SDK streams the JSON response directly to your React components. The user watches the call queue numbers update live.

You want custom UI components. This server lets you build specific supervisor views in Next.js that only show what your floor managers actually need.

You pass a prompt asking for specific teams, and the agent uses `list_agent_teams` followed by `get_team_details`. The SDK handles the tool chaining and streams the final roster to your frontend.

Your call recordings and agent metadata never hit our storage disks. The V8 Isolate Sandbox processes the audio URLs in memory and destroys the instance immediately after the Vercel AI SDK receives the payload.

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