How to Use the Chaindesk MCP in Vercel AI SDK

Q: How do I pass Chaindesk tools to Vercel AI SDK?

Run npm install @ai-sdk/mcp. Initialize the client with createMCPClient pointing to your Vinkius HTTP URL, call mcpClient.tools(), and pass the array straight into generateText or streamText.

Q: Can Vercel AI SDK stream Chaindesk responses to Next.js?

Yes. When your prompt triggers queryagent, the SDK streams the text chunks back to the browser. Your React components render the output in real-time.

Q: How do I close the Chaindesk MCP connection in Vercel AI SDK?

Always append mcpClient.close() after your generation finishes. Keeping idle connections open wastes resources.

Connect Chaindesk to Vercel AI SDK to build customer support interfaces that stream custom knowledge base answers live to users.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Chaindesk MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Chaindesk MCP Server answers to React

Building a Next.js chat interface means you want text appearing immediately. When you connect this server, your frontend calls `query_agent` and pipes the output straight into the UI components. Users read the response while the model is still thinking. You do not have to build custom API routes for every backend action. Fetching context via `get_datastore` or pulling chat history with `get_messages` happens right inside your tool calling loop. The Vercel AI SDK handles the state management automatically.

Update knowledge bases from user input

Static FAQs get outdated fast. By exposing `upsert_datasource` to your frontend application, authorized users can dump new text or links directly into your datastores. The system indexes the new material instantly. This MCP Server ensures your customer support bot gets smarter without deploying new code. Agents created via `create_agent` immediately start referencing the fresh context.

Render past chat sessions instantly

Returning visitors expect to see their old tickets. Your application can fire off `list_conversations` filtered by a specific agent ID to populate the sidebar. Pulling the exact thread is just a matter of running `get_messages`. Because Vinkius handles the underlying MCP connection, your token works across all edge functions without complex authentication flows.

Setup guide

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

Run `npm install @ai-sdk/mcp`. Initialize the client with `createMCPClient` pointing to your Vinkius HTTP URL, call `mcpClient.tools()`, and pass the array straight into `generateText` or `streamText`.

Yes. When your prompt triggers `query_agent`, the SDK streams the text chunks back to the browser. Your React components render the output in real-time.

Vinkius MCP endpoints are standard HTTP. Your edge functions can call `list_agents` or `get_datastore` without bringing in heavy Node.js dependencies.

Always append `mcpClient.close()` after your generation finishes. Keeping idle connections open wastes resources.

Support transcripts and internal documentation stay locked down. The V8 Isolate Sandbox destroys the environment after execution, meaning your datastore IDs and system prompts never linger in memory.

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