How to Use the CallFire MCP in Vercel AI SDK

Q: How do I connect CallFire to Vercel AI SDK?

Install both @ai-sdk/mcp and the core ai package via npm. You instantiate the client using createMCPClient with your Vinkius HTTP transport URL. Pass the resulting tool set into streamText to start interacting with your telephony data.

Stream live SMS and voice campaign data directly into your React frontends using the CallFire MCP Server for 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 CallFire MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream CallFire MCP Server Data to React

The `list_calls` and `list_sent_sms` tools pull recent communication logs straight from your account. Vercel AI SDK passes this data through your Edge Functions and pushes it to the client side. Your users watch their messaging history populate instantly on screen instead of staring at a blank loading state. Calling `get_account_info` streams your resulting balances and limits into your Next.js dashboard components as the chunks arrive. That immediate feedback loop keeps users engaged while heavy backend queries finish. We built this to solve the delay inherent in fetching bulk telephony records.

Trigger SMS and Voice from Edge Functions

The `send_sms` tool dispatches text messages directly from your Svelte or Vue application. You configure your tool block, and the AI agent evaluates the user prompt to fire off the exact message required. The UI immediately reflects the action without forcing a manual page refresh. Executing `send_voice_call` initiates an outbound phone call based on the agent's logic. You run this through Vercel's streaming architecture to get the confirmation ID back in milliseconds. Developers render the active call status right in the browser.

Live Campaign Sound and Webhook Tracking

The `list_campaign_sounds` tool retrieves all audio files configured for outbound dialing. Your AI client reads this list and helps users select the right recording for their next broadcast. You pass the selection back through the SDK to update the campaign settings on the fly. Executing `list_webhooks` pulls down every active endpoint listening for call completions or text replies. The Vercel AI SDK renders those configurations as interactive tables. Your team can verify payload destinations directly from the frontend.

Setup guide

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

Install both `@ai-sdk/mcp` and the core `ai` package via npm. You instantiate the client using `createMCPClient` with your Vinkius HTTP transport URL. Pass the resulting tool set into `streamText` to start interacting with your telephony data.

Yes, it pushes the exact delivery status and message body straight to the frontend. You call `get_sms_details` with the specific message ID. The SDK streams that payload into your UI components as fast as the endpoint returns it.

Long-running bulk operations need background processing, not synchronous edge calls. Use the SDK to trigger alerts for individual users. Then rely on webhooks to handle the asynchronous delivery receipts.

Never expose your API keys to the browser. Vinkius handles the underlying provider authentication inside its isolated environment. Your server-side code just passes the single endpoint token to the MCP Server.

Every phone number, message body, and audio file identifier stays strictly within the Vinkius V8 Isolate Sandbox. We spin up an ephemeral container for your specific request and destroy it immediately after execution. Your proprietary campaign data never rests on our disks.

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