How to Use the ArcXP MCP in Vercel AI SDK

Q: How do I use the Vercel AI SDK to search for ArcXP articles?

You'll call generateText or streamText and give your agent access to the searchanscontent tool. The agent uses the tool to query ArcXP, and the results stream back to your application as structured JSON.

Q: Can I create new ArcXP content from my Next.js app?

Yes. Your agent needs the createanscontent tool. You'll construct the Arc Native Schema (ANS) object in your code and pass it as the argument. The tool handles the API call to ArcXP.

Q: Is it possible to build a live author dashboard for ArcXP with the Vercel AI SDK?

Definitely. You can use the listcontentauthors tool to get a list of all authors and then use getcontentauthor to fetch details for specific ones. The SDK's streaming capabilities let you populate your UI components with this data as it arrives.

Q: What's the best way to handle ArcXP photo assets using the Vercel AI SDK?

Use the searchphotoassets tool to find images based on keywords. The tool returns metadata, including image URLs. You can then use these URLs directly in your React or Next.js components to display the photos.

Stream ArcXP content directly into your React components with the Vercel AI SDK, showing data as it arrives.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ArcXP MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Live Content Previews

Stop showing loading spinners. Use the Vercel AI SDK to stream content from ArcXP directly into your UI components. Your agent can call `search_ans_content` or `get_ans_content`, and your users will see article text and data appearing in real-time. This isn't just for text. You build a component, connect it to the MCP server, and watch as your agent populates it with live data. It's a much better user experience, and it's built right into the SDK's streaming functions.

Manage Content from Your Frontend

Give your users tools to manage their ArcXP content without leaving your app. You can build an interface that lets them edit, create, or update articles. Your agent handles the rest. Behind the scenes, your agent will take the user's input, format it into a valid Arc Native Schema payload, and use the `create_ans_content` or `update_ans_content` tools to push the changes. You just build the UI; the MCP server provides the backend connection.

Integrate the Media Library with the Vercel AI SDK

Build a custom media picker for your app. With this MCP server, your agent gets direct access to the ArcXP Media Library. You can use `search_photo_assets` to find images or `get_video_asset` to pull a specific video. Because the AI SDK streams results, you can build a search interface that feels incredibly fast. As the agent finds matching photos, they appear in your UI one by one. The tool returns all the metadata you need, including URLs for `<img>` tags.

Setup guide

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

You'll call `generateText` or `streamText` and give your agent access to the `search_ans_content` tool. The agent uses the tool to query ArcXP, and the results stream back to your application as structured JSON.

Yes. Your agent needs the `create_ans_content` tool. You'll construct the Arc Native Schema (ANS) object in your code and pass it as the argument. The tool handles the API call to ArcXP.

Definitely. You can use the `list_content_authors` tool to get a list of all authors and then use `get_content_author` to fetch details for specific ones. The SDK's streaming capabilities let you populate your UI components with this data as it arrives.

Use the `search_photo_assets` tool to find images based on keywords. The tool returns metadata, including image URLs. You can then use these URLs directly in your React or Next.js components to display the photos.

Your connection only ever touches the ArcXP data your agent explicitly requests, like ANS JSON objects and media asset metadata. Vinkius secures the transport with a single endpoint token, and each request runs in an ephemeral sandbox. Your application's data is never exposed.

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