How to Use the Thoughtly MCP in Vercel AI SDK

Stream Thoughtly voice data directly into your Vercel AI SDK interface for real-time interaction logs.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Thoughtly MCP to Vercel AI SDK

Create your Vinkius account to connect Thoughtly to Vercel AI SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Thoughtly with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Real-time voice agent orchestration

Trigger outbound calls directly from your frontend using `trigger_call` to initiate conversations. Your users watch status updates flow into the UI without waiting for page refreshes. Connect these events to your state management to handle complex call flows. This keeps your interface responsive while the background processes manage the telephony.

Live CRM data management

Pull contact information into your components using `list_contacts` and `get_contact`. Update records instantly when a user changes their details via `update_contact` or `create_contact`. Everything stays synced with your database. You see the changes reflected in your dashboard as soon as the API confirms the write.

Instant call history retrieval

Display past interactions by calling `list_calls` to populate your activity feed. Fetch transcripts and specific metrics using `get_call_history` to show detailed performance data. Your users gain context on every lead. They can review interview summaries fetched via `get_interview` to understand why a call succeeded or failed.

Setup guide

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

Install the MCP package and point the client to your server endpoint. You then pass the exposed tools directly into your `generateText` function to enable voice control.

Yes. The transport layer handles the connection, allowing your edge functions to execute tool calls. Ensure your environment variables for the server are set correctly.

You can. By streaming results into your React components, you show the AI's progress as it handles contacts and calls. It makes the backend operations feel like a native part of your app.

Transcripts reside in the secure backend managed by Thoughtly. You access the raw text via the MCP server whenever you need it for your interface.

We enforce strict isolation for every connection. Your contact records and call logs remain encrypted and are only accessible through your authenticated MCP token.

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