How to Use the Cincopa MCP in Vercel AI SDK

Q: How does the Vercel AI SDK connect to Cincopa?

You use the @ai-sdk/mcp package to create a client pointed at your Vinkius endpoint URL. Vinkius handles the Cincopa authentication for this MCP server. You just pass the tools from the client to the streamText or generateText functions.

Q: Can I build a UI that lets users create Cincopa galleries with the Vercel AI SDK?

Yes, that's a perfect use case. Your agent can use the createnewgallery tool. You can build a simple form in your React app that collects a name, and the agent handles the API call.

Q: Can I filter which Cincopa assets are shown in my Vercel AI SDK app?

Your agent fetches the full list with listcincopaassets. You can then instruct your agent in your prompt to filter those results based on metadata, date, or name before streaming them to the UI.

Build live media dashboards in your Next.js app with Cincopa and 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 Cincopa MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Gallery Data into Your UI

Your agent calls `list_cincopa_galleries` and the AI SDK streams the results directly into your React components. Users see their galleries appear one by one, not after a loading spinner. It feels instant. When a user clicks a gallery, your agent can call `get_gallery_details` and `list_cincopa_assets` to populate the view. Thumbnails and metadata appear live on the screen, creating a much more responsive front-end than old-school data fetching.

Create Interactive Media Managers

Go beyond just viewing data. Use the AI SDK to build an interface where your agent can act on user requests. A user could ask to "create a new gallery for the summer campaign," and your agent would use `list_cincopa_templates` to show options, then `create_new_gallery` to build it. This turns a static page into a dynamic workspace. You can even add a button that triggers your agent to call `get_media_upload_url`, letting users upload files directly into your Cincopa account from your app.

Real-time Asset Status with this MCP Server

Give your users real-time feedback. After an upload, your agent can poll the `get_asset_metadata` tool. The AI SDK's streaming capabilities mean you can show a "Processing..." status in the UI and have it update to "Ready" the moment the data changes. This also works for deletions. When a user deletes a file, your agent calls `delete_media_asset`. You can immediately remove the item from the UI and show a confirmation, because the action happens through the agent, not a separate API call you have to track.

Setup guide

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

You use the `@ai-sdk/mcp` package to create a client pointed at your Vinkius endpoint URL. Vinkius handles the Cincopa authentication for this MCP server. You just pass the tools from the client to the `streamText` or `generateText` functions.

Yes, that's a perfect use case. Your agent can use the `create_new_gallery` tool. You can build a simple form in your React app that collects a name, and the agent handles the API call.

Absolutely. Your Vercel app communicates with your agent, which then connects to the Vinkius MCP Server through a secure endpoint. Your Cincopa credentials are never exposed to the browser or your front-end code.

Your agent fetches the full list with `list_cincopa_assets`. You can then instruct your agent in your prompt to filter those results based on metadata, date, or name before streaming them to the UI.

This server only interacts with your Cincopa media assets, galleries, and templates. All connections are made through the sandboxed Vinkius environment, which isolates each request. Your private Cincopa API keys are encrypted and never leave the Vinkius backend.

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