How to Use the CallFire MCP in Vercel AI SDK

Q: How do I stream CallFire text histories in Vercel AI SDK?

You pass the server tools directly to streamText or generateText using the MCP client wrapper. The AI client calls listtexts or gettext and streams the JSON payload directly into your React components. Don't forget to call mcpClient.close() once the generation finishes to clean up your connections.

Q: How does Vercel AI SDK handle CallFire webhook configurations?

Your agent can inspect active webhooks by calling listwebhooks through the SDK tools interface. If you need to verify a specific endpoint configuration, the agent invokes getwebhook and returns the target URL and event triggers directly to your terminal or UI.

Q: What happens if a voice broadcast call fails during retrieval?

Your application catches the error thrown by getcall within the SDK's execution block. You can design your model prompt to explain the error to the user or automatically try listing alternative calls using listcalls instead.

Q: How does Vercel AI SDK protect my CallFire contact data?

All transmission of your contacts fetched via getcontact or listcontacts happens over encrypted HTTPS channels. Vinkius isolates the execution environment so that customer phone numbers and names are never cached or exposed to third parties.

Let your Vercel AI SDK app stream live CallFire campaign metrics and text logs straight to your users without loading spinners.

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

Live Campaign Feeds in Vercel AI SDK

This MCP Server exposes voice broadcast tools like `list_campaigns` so your Next.js frontend can pull data chunk by chunk as it arrives from the gateway. Stop making users wait for heavy API payloads to resolve. By passing the toolset to `streamText`, your UI updates instantly as the AI client pulls the specific campaign via `get_campaign`. Users watch their outbound call statistics populate in real-time right on the dashboard.

Instant Text Log Inspections

This MCP Server exposes message tools like `get_text` to immediately fetch the exact message thread. When support agents ask about a specific customer interaction, your AI client can trigger this query and drop the payload into the chat interface without freezing the browser tab. Because Vercel AI SDK runs on edge infrastructure, these calls execute with minimal latency. Your agent searches through thousands of records using `list_texts` and presents the filtered history to your team in milliseconds.

On-the-Fly Contact Lookup

This MCP Server exposes contact tools like `get_contact` to pull customer phone records and names directly into the active LLM context window while the user is typing. Building a custom CRM view with this MCP toolset requires fast data fetching. The AI client handles the heavy lifting by scanning your address book with `list_contacts` to find matches. It formats the raw JSON into interactive UI components on your frontend before the user even finishes their search query.

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

You pass the server tools directly to `streamText` or `generateText` using the MCP client wrapper. The AI client calls `list_texts` or `get_text` and streams the JSON payload directly into your React components. Don't forget to call `mcpClient.close()` once the generation finishes to clean up your connections.

Yes. The server is fully compatible with edge runtimes when configured with the Vercel AI SDK. You initialize the client using `createMCPClient` with an HTTP transport, allowing your serverless functions to fetch `get_campaign` data without cold-start delays.

Your agent can inspect active webhooks by calling `list_webhooks` through the SDK tools interface. If you need to verify a specific endpoint configuration, the agent invokes `get_webhook` and returns the target URL and event triggers directly to your terminal or UI.

Your application catches the error thrown by `get_call` within the SDK's execution block. You can design your model prompt to explain the error to the user or automatically try listing alternative calls using `list_calls` instead.

All transmission of your contacts fetched via `get_contact` or `list_contacts` happens over encrypted HTTPS channels. Vinkius isolates the execution environment so that customer phone numbers and names are never cached or exposed to third parties.

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