How to Use the Showpad MCP in Vercel AI SDK

Q: How do I search for assets using the Showpad MCP Server with ai-sdk?

You call mcpClient.tools().searchassets(keyword). The result streams directly into your React component, giving immediate visual feedback to the user without needing a separate API call or loading state.

Q: Can I list users in Showpad and display that data using ai-sdk?

Yep. Calling listusers populates your agent client with an array of all showpad user objects. You can then iterate over this list to build a directory component or a select input.

Q: What data does the Showpad MCP Server provide for asset governance in ai-sdk?

The server provides both granular details via getassetdetails and broad lists using listassets. This lets you show users exactly what an asset is, while also giving them a quick overview of all available content.

Q: How do I list channels in Showpad for my front-end product with ai-sdk?

Just call listchannels. The results are typed and stream back to your client, letting you populate channel selection components right in Next.js or Svelte.

Q: If I need to check Showpad permissions for a user using ai-sdk, how should I proceed?

Use getuserdetails first to verify the account exists and grab core profile data. You can then use that ID in conjunction with other tools to see what content they have access to.

Display Showpad data in real time with the TypeScript SDK for client-side streaming.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Showpad MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Find specific content assets fast.

Use `search_assets` to query the entire corpus of sales collateral by keyword. You pass a search term, and the MCP Server returns matching asset IDs and metadata instantly. This means you get real-time data updates in your UI. Your agent client sees results appear immediately, bypassing traditional loading spinners.

Track users and organizational structure.

The `get_user_details` tool fetches specific user information from Showpad based on an ID. This lets you build components that show current team roles or contact details as the user interacts with them. Similarly, running `list_users` provides a complete list of all accounts within your organization, letting your agent client populate dropdown menus and selection fields.

Get metadata for any Showpad asset.

`get_asset_details` retrieves the full details for one specific piece of content. It's better than just listing IDs because it gives you context—like version numbers or owner information. You can also use `list_tags` to pull all available classification tags, letting your UI dynamically build filtering options based on Showpad's taxonomy.

Setup guide

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

You call `mcpClient.tools().search_assets(keyword)`. The result streams directly into your React component, giving immediate visual feedback to the user without needing a separate API call or loading state.

Yep. Calling `list_users` populates your agent client with an array of all showpad user objects. You can then iterate over this list to build a directory component or a select input.

The server provides both granular details via `get_asset_details` and broad lists using `list_assets`. This lets you show users exactly what an asset is, while also giving them a quick overview of all available content.

Just call `list_channels`. The results are typed and stream back to your client, letting you populate channel selection components right in Next.js or Svelte.

Use `get_user_details` first to verify the account exists and grab core profile data. You can then use that ID in conjunction with other tools to see what content they have access to.

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