How to Use the MediaSilo MCP in Vercel AI SDK

Q: How do I stream MediaSilo video assets using Vercel AI SDK?

Call mcpClient.tools() and pass them to streamText. Your frontend will render the asset list returned by listassets as the model finds them, meaning zero load lag for your users.

Q: Can I search folders using this MCP Server with Vercel AI SDK?

Yes. You can query searchassets or listfolders inside your Next.js API routes. The results stream back to the UI block by block, updating the client search interface immediately.

Q: What happens when a user requests a MediaSilo shared link in Vercel AI SDK?

The client calls getquicklink to grab the secure URL. It streams the metadata to your React component, which renders the playable review link on the fly.

Q: How do I close the connection to avoid memory leaks?

Always call mcpClient.close() once your streaming session wraps up. This releases the MCP Server HTTP transport and avoids hanging connections on your Edge Functions.

Stream MediaSilo assets directly into your React and Next.js frontends using 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 MediaSilo MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live-stream MediaSilo folders to your UI

Users hate waiting for spinners while a server fetches large video directories. This MCP integration lets you run `list_folders` and `list_projects` in real-time, sending folders straight to the user's browser before the full page loads. By using Edge-compatible functions, your Next.js app renders project trees as they arrive. If a user needs a specific file, the agent uses `get_project_assets` to populate the workspace instantly.

Instant metadata rendering in Vercel AI SDK

When an editor looks for a file, they need technical specs immediately. This server lets your application run `get_asset` and `search_assets` to pull video metadata directly into custom UI components. The client displays resolution, framerate, and upload dates without forcing anyone to log into the main platform. It makes building custom review portals straightforward.

Resolve Quicklinks in real-time

Sharing files usually takes too many clicks. By pairing the MCP Server with your interface, you can call `get_quicklink` and `list_quicklinks` to display active share links side-by-side with your video player. This stops users from digging through email threads to find review pages. The links appear as soon as the agent fetches them, keeping the work moving.

Setup guide

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

Call `mcpClient.tools()` and pass them to `streamText`. Your frontend will render the asset list returned by `list_assets` as the model finds them, meaning zero load lag for your users.

Yes. You can query `search_assets` or `list_folders` inside your Next.js API routes. The results stream back to the UI block by block, updating the client search interface immediately.

The client calls `get_quicklink` to grab the secure URL. It streams the metadata to your React component, which renders the playable review link on the fly.

Always call `mcpClient.close()` once your streaming session wraps up. This releases the MCP Server HTTP transport and avoids hanging connections on your Edge Functions.

Your MediaSilo video metadata, project folders, and user emails never touch third-party databases. The server processes these tokens inside an isolated sandbox, keeping your private production assets safe.

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