How to Use the Daktela MCP in Vercel AI SDK

Q: How do I connect Daktela to my Vercel AI SDK project?

Install @ai-sdk/mcp and call createMCPClient with your Vinkius MCP endpoint. Pass the tools directly to streamText and remember to call mcpClient.close() when the session ends.

Q: Can I stream Daktela call histories with Vercel AI SDK?

Yes, you feed listcallhistory into your streaming text function to show live logs in your UI. The Vercel AI SDK renders the phone records block-by-block as the server sends them.

Q: What is the best way to handle OAuth authentication?

Use the SDK's authProvider option when initializing your client. It injects the required tokens securely for every MCP session, allowing safe access to getme and other personal endpoints.

Pipe Daktela call logs and support tickets directly into your React components in real time 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 Daktela MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed real-time ticket updates to your Vercel AI SDK UI

The `get_ticket` tool pulls the exact status of any Daktela support ticket. Your React app displays this data immediately as the Vercel AI SDK streams the response. No loading spinners, no waiting. You feed `list_tickets` straight into `streamText` to populate customer dashboards on the fly. This setup runs inside Edge Functions, keeping the UI fast while your agent resolves customer queries.

Spawn CRM contacts directly from live chat

The `create_contact` tool registers new customer profiles in your Daktela CRM during active conversations. Your frontend updates the customer list instantly because the Vercel AI SDK handles tool outputs as direct UI state changes. Combining this with `list_accounts` lets your agent check company associations before writing new data. You get a clean interface where users watch the CRM update in real time without refreshing.

Build live queue monitors with this MCP Server

This MCP Server uses `list_queues` to expose live contact center queues directly to your interface. Agents see incoming call volume shifts as they happen, because the SDK handles the data flow without backend bloat. We use `list_call_history` alongside it to give agents immediate context on past missed calls. It makes your support dashboard feel alive, running entirely on edge-compatible runtime calls.

Setup guide

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

Install `@ai-sdk/mcp` and call `createMCPClient` with your Vinkius MCP endpoint. Pass the tools directly to `streamText` and remember to call `mcpClient.close()` when the session ends.

Yes, you feed `list_call_history` into your streaming text function to show live logs in your UI. The Vercel AI SDK renders the phone records block-by-block as the server sends them.

The server runs as a lightweight HTTP endpoint hosted by Vinkius, making it fully compatible with edge runtimes. Your Vercel AI SDK code stays small and fast since it doesn't bundle heavy Daktela API clients.

Use the SDK's `authProvider` option when initializing your client. It injects the required tokens securely for every MCP session, allowing safe access to `get_me` and other personal endpoints.

Your support tickets, CRM contacts, and call logs are processed inside ephemeral V8 isolates on Vinkius. No customer data or communication history is stored on our servers, ensuring your raw CRM details remain private.

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