How to Use the Craft.io MCP in Vercel AI SDK

Q: How do I configure the Vercel AI SDK to pull from the Craft.io MCP Server?

Install @ai-sdk/mcp and initialize the client with your Vinkius HTTP endpoint. Pass the tools directly into streamText or generateText so your model calls listitems on demand. Remember to call mcpClient.close() once the stream finishes to clean up active connections.

Q: Can I use Vercel AI SDK UI components to display Craft.io roadmaps?

Yes, you map the tool outputs from getitem directly to your custom React components. The SDK streams the tool arguments and results, allowing your UI to render the workspace items before the model even finishes generating its text response.

Q: What happens if the connection to the workspace fails?

You should call checkcraftstatus first to verify the API is reachable. If the status check fails, your application catches the error and displays a clean fallback UI instead of breaking the text stream.

Q: How does this MCP setup protect my company financial data?

Your company financials and competitor lists fetched via getcompanyfinancials never touch public logs. Vinkius runs the connector in an isolated, ephemeral V8 container that wipes itself clean the moment your Vercel AI SDK session ends.

Build real-time product roadmaps directly in your Next.js frontend using the Vercel AI SDK and Craft.io data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Craft.io MCP to Vercel AI SDK

Create your Vinkius account to connect Craft.io 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 Craft.io with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Craft.io items directly to React UIs

The `create_item` tool lets your Vercel AI SDK application build workspace items live on the screen. Instead of waiting for a slow API response to finish, users watch their product roadmap populate step-by-step as the AI client writes. This means you hook up `list_workspaces` to a dropdown and let users instantly see their active workspaces. The MCP streaming interface feels instant because the data pipes straight into your frontend components without loading states.

Live financial and competitor feeds with MCP Server tools

The `get_company_financials` and `get_company_competitors` tools bring raw market intelligence straight into your streaming interface. Fetching market intel shouldn't freeze your UI when calling external resources. Your users get immediate feedback. They search for a company, and the Vercel AI SDK renders the financial breakdown block-by-block, making the entire search experience feel incredibly fast.

Interactive portfolio mapping on the Edge

The `list_portfolios` and `get_portfolio` tools run inside lightweight V8 sandboxes directly on Vercel Edge Functions. Run your product discovery tools on edge runtimes without hitting cold starts or latency penalties. You don't have to write complex wrapper APIs. Just pass the tools to your Vercel AI SDK model call, and let the edge runtime handle the secure connection to your MCP Server.

Setup guide

Set up Craft.io 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 Craft.io 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 Craft.io 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 Craft.io. 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 Craft.io 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 Craft.io MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and initialize the client with your Vinkius HTTP endpoint. Pass the tools directly into `streamText` or `generateText` so your model calls `list_items` on demand. Remember to call `mcpClient.close()` once the stream finishes to clean up active connections.

Yes, you map the tool outputs from `get_item` directly to your custom React components. The SDK streams the tool arguments and results, allowing your UI to render the workspace items before the model even finishes generating its text response.

It does when you configure the client with an authProvider. The SDK handles user token exchange, allowing your frontend to safely run tools like `create_item` on behalf of the logged-in user.

You should call `check_craft_status` first to verify the API is reachable. If the status check fails, your application catches the error and displays a clean fallback UI instead of breaking the text stream.

Your company financials and competitor lists fetched via `get_company_financials` never touch public logs. Vinkius runs the connector in an isolated, ephemeral V8 container that wipes itself clean the moment your Vercel AI SDK session ends.

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