How to Use the ThinkStack MCP in Vercel AI SDK

Q: How do I verify my ThinkStack connection when using the Vercel AI SDK?

Call checkthinkstackstatus early in your client lifecycle. This endpoint confirms that the MCP Server is reachable and ready for live data streaming before you even attempt a query.

Q: Can I list all available chatbots with ThinkStack using the Vercel AI SDK?

Yep, just use the listbots tool. It returns metadata for every bot configured in your ThinkStack environment, letting you build a directory or selector page into your app.

Q: Does ThinkStack support streaming responses with the Vercel AI SDK?

Absolutely. The core design allows results from tools like sendquery to stream directly into your frontend, bypassing traditional loading spinners for a much better user experience.

Q: What if I need to audit past conversations with ThinkStack and the Vercel AI SDK?

You can pull conversation history using listconversations or fetch details on a specific thread with getconversation. This lets you build moderation tools that review user interactions.

Stream live data from ThinkStack's MCP Server directly into your Next.js frontend using the Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect ThinkStack MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Chat Interactions with ThinkStack and the Vercel AI SDK

The `send_query` tool lets you stream a chatbot's response directly into your React UI. You call this function, and instead of waiting for a single payload, your user sees text appearing character by character—perfect for real-time chat experiences. You can track the entire interaction history using tools like `get_conversation` or list past chats with `list_conversations`. This lets you build robust client features that display contextually relevant data as it streams in.

Managing Knowledge Sources via MCP Server

Need to update the bot's knowledge base? The `add_source` tool indexes new content automatically, letting your chatbot answer questions based on the latest material. You can audit what sources are connected using `list_sources`, or remove old data with `delete_source`. This gives you fine control over the data feeding the MCP Server. When you're ready to build out a knowledge-driven product, managing these inputs is critical.

Monitoring and Auditing Bot Status

Start by checking connectivity with `check_thinkstack_status` before deploying your app; this ensures the MCP Server link is solid. You can also pull specific bot details using `get_bot` or see a list of all available bots via `list_bots`. It’s good practice to check these endpoints first. When debugging, running `list_actions` shows you every action the bot supports. This helps your client code know exactly what capabilities it can call through the MCP Server.

Setup guide

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

Call `check_thinkstack_status` early in your client lifecycle. This endpoint confirms that the MCP Server is reachable and ready for live data streaming before you even attempt a query.

Yep, just use the `list_bots` tool. It returns metadata for every bot configured in your ThinkStack environment, letting you build a directory or selector page into your app.

The server handles knowledge source identifiers and status flags. You can see what's connected by calling `list_sources`, which gives you a manifest of all indexed content.

Absolutely. The core design allows results from tools like `send_query` to stream directly into your frontend, bypassing traditional loading spinners for a much better user experience.

You can pull conversation history using `list_conversations` or fetch details on a specific thread with `get_conversation`. This lets you build moderation tools that review user interactions.

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