How to Use the GPTBots MCP in Vercel AI SDK

Q: How do I connect the GPTBots MCP Server to Vercel AI SDK?

Install the packages using npm install ai @ai-sdk/mcp first. Next, instantiate the client with createMCPClient using your HTTP endpoint. Finally, call mcpClient.tools() and pass them to streamText before calling mcpClient.close() at the end of the execution.

Q: How do I render the list of GPTBots chat logs using Vercel AI SDK?

Call listconversations via your agent tools to get the raw metadata array. The Vercel AI SDK streams this array straight to your UI components, letting you render a live sidebar of past chats without writing custom fetch handlers.

Q: What is the best way to handle authentication with this setup?

Use the authProvider option inside your client configuration to pass user tokens. This secures your calls to sendbotmessage and ensures that users only access their authorized workspace data via MCP.

Stream live conversational data and database tables directly to your React components 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 GPTBots MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Direct UI updates from raw knowledge base files

`create_knowledge_document` lets your frontend application ingest user files directly into your vector storage without backend middle layers. Your agent processes the raw text, pushes it to your knowledge base, and updates the UI status immediately. You don't have to build custom polling mechanisms to check if the ingestion finished. Instead, use `list_knowledge_documents` to pull the updated document directory and render the refreshed list in your Next.js dashboard right away.

Expose live database schemas to the Vercel AI SDK

`list_databases` exposes the structural tables of your platform database directly to your frontend agent. This allows your user-facing UI to render schema visualizations on the fly as the agent inspects the database. Passing these tools directly into `streamText` means your users see exactly which tables the agent is querying. The MCP Server executes the database lookup, and the schema metadata streams straight to your component props.

Stream active chat sessions without custom API routes

`send_bot_message` delivers messages to your active agents and returns their responses directly to your streaming frontend. You bypass the need to write custom wrapper APIs for your messaging flows. Session state remains clean because `get_conversation` and `list_conversations` fetch historical chat logs on demand. This keeps your React state in sync with the actual platform history without local database bloat.

Setup guide

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

Install the packages using `npm install ai @ai-sdk/mcp` first. Next, instantiate the client with `createMCPClient` using your HTTP endpoint. Finally, call `mcpClient.tools()` and pass them to `streamText` before calling `mcpClient.close()` at the end of the execution.

Yes, the HTTP transport works natively in Vercel Edge Environments. You trigger background jobs with `trigger_workflow` and monitor them using `query_workflow` without hitting timeout limits. The runtime stays lightweight because the MCP Server handles the heavy execution.

Call `list_conversations` via your agent tools to get the raw metadata array. The Vercel AI SDK streams this array straight to your UI components, letting you render a live sidebar of past chats without writing custom fetch handlers.

Use the `authProvider` option inside your client configuration to pass user tokens. This secures your calls to `send_bot_message` and ensures that users only access their authorized workspace data via MCP.

The server limits database access to metadata inspection when using `list_databases`. All schema queries run inside isolated V8 sandboxes on the Vinkius platform, ensuring your raw database credentials never leak to the client side. This zero-trust MCP execution layer protects your infrastructure.

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