How to Use the Kavkom MCP in Vercel AI SDK

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

You initialize the connection using createMCPClient. Point the transport URL to your Vinkius endpoint. Then pass the extracted tools directly into generateText or streamText.

Q: Does the Vercel AI SDK support Kavkom SMS sending?

It does. You expose sendsmsmessage to your agent. The user prompts the agent to send a text, and the framework executes the API call.

Stream Kavkom call data and SMS history straight into your Next.js frontends with 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 Kavkom MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream call logs to the UI

`list_calls` and `get_call_details` pull raw telephony records directly from the API. Your Next.js app doesn't need to wait for a massive JSON payload to finish downloading. You pass these tools to `streamText`, and the client renders individual call logs as they arrive. Users see the phone numbers, timestamps, and durations populating their dashboard in real-time. This eliminates loading spinners entirely. You get a snappy, modern interface that feels instant because the data actually is.

Manage address books at the Edge

`list_crm_contacts` and `create_contact` handle your account directory operations. You build a chat interface where a user asks to add a new lead, and the agent executes the tool instantly. The Vercel AI SDK manages the tool calling loop under the hood. Edge functions support this setup perfectly. You spin up the connection, fire off the contact creation, and close it down. Your frontend stays fast, and your backend avoids unnecessary bloat.

Send texts from React components

`send_sms_message` and `list_sms_history` give your AI client text messaging capabilities. A user types a message into your React component, and the agent fires the text via the API. The SDK streams the confirmation back to the UI immediately. Setting this MCP Server up requires minimal boilerplate. You run `createMCPClient`, point it at the Vinkius endpoint, and extract the tools. Always remember to call `mcpClient.close()` when the transaction finishes.

Setup guide

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

You initialize the connection using `createMCPClient`. Point the transport URL to your Vinkius endpoint. Then pass the extracted tools directly into `generateText` or `streamText`.

Yes. The SDK handles streaming natively. When the agent calls `list_calls`, the results pipe directly into your frontend without waiting for the entire response to finish.

It does. You expose `send_sms_message` to your agent. The user prompts the agent to send a text, and the framework executes the API call.

The SDK surfaces the error to your application code. You can catch this exception and render a fallback UI for the user.

Vinkius runs every request inside a V8 Isolate Sandbox. Your call logs never touch a shared file system. The instance terminates the millisecond the API returns the data.

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