How to Use the Macaulay Library MCP in Vercel AI SDK

Q: How do I search for specific bird songs from the Macaulay Library using the Vercel AI SDK?

You prompt your agent to use the searchmedia tool with the species name and specify the media type as 'audio'. The AI SDK will stream the resulting asset IDs, which you can then use with getasset to fetch and display details in your UI.

Q: Can I build a real-time map of bird sightings with this?

Yes. Your agent can use searchmedia to find assets and then getasset to get the GPS coordinates for each one. With the Vercel AI SDK, you can stream these coordinates directly to a mapping component in your Next.js app.

Q: What's the best way to show the newest Macaulay Library uploads in my Vercel AI SDK app?

Use the getrecentmedia tool. Your agent can call it to get a list of the latest assets. Then, you can use the AI SDK's streaming capabilities to render a live-updating feed of new wildlife recordings in your application.

Stream animal sounds and video metadata directly into your Vercel AI SDK app. Build real-time biodiversity dashboards, not loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Macaulay Library MCP to Vercel AI SDK

Create your Vinkius account to connect Macaulay Library 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 Macaulay Library with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Find Any Species, Instantly

The `search_media` tool connects your AI client directly to the world's largest wildlife media archive. You can ask for audio of a specific bird, like the Northern Cardinal, and get back a list of asset IDs ready for the next step. Because you're using the Vercel AI SDK, you can stream these results directly into your React or Svelte components. Imagine a user typing a species name and seeing a grid of photos and audio players populate in real time as your agent works. That's what this setup gives you.

Get Rich Metadata for Your UI

Once you have an asset ID from a search, the `get_asset` tool fetches all the details. This isn't just a filename; you get precise GPS coordinates, the date and time of the recording, observer notes, and even the equipment used. This is where the Vercel AI SDK shines. You can build a UI that shows a map with the recording location, a timeline of sightings, and detailed taxonomic information, all streamed directly from the MCP Server as the data arrives. Your users see a living interface, not a static page.

Monitor New Sightings Live

Use the `get_recent_media` tool to build a live feed of new uploads to the library. Your agent can check for the latest bird calls, mammal sounds, or insect videos from specific regions, giving you a near real-time pulse on what's being observed. This is perfect for creating a “latest sightings” feature in your frontend. Your AI client can periodically call this tool and stream the newest assets straight into your UI, keeping your application's content fresh and engaging without any manual updates.

Setup guide

Set up Macaulay Library 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 Macaulay Library 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 Macaulay Library 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 Macaulay Library. 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 Macaulay Library 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 Macaulay Library MCP in Vercel AI SDK

You prompt your agent to use the `search_media` tool with the species name and specify the media type as 'audio'. The AI SDK will stream the resulting asset IDs, which you can then use with `get_asset` to fetch and display details in your UI.

Yes. Your agent can use `search_media` to find assets and then `get_asset` to get the GPS coordinates for each one. With the Vercel AI SDK, you can stream these coordinates directly to a mapping component in your Next.js app.

Use the `get_recent_media` tool. Your agent can call it to get a list of the latest assets. Then, you can use the AI SDK's streaming capabilities to render a live-updating feed of new wildlife recordings in your application.

Yes. The server is hosted on Vinkius, designed for low latency. When your agent calls a tool like `search_media`, the response is immediate, making it ideal for the real-time, interactive experiences you build with the Vercel AI SDK.

Your app and the Vercel AI SDK client never directly touch Macaulay Library credentials. Your Vinkius endpoint token secures the connection to the MCP Server, which handles authentication. The data in transit is asset metadata—like species names, locations, and quality ratings—all encrypted over TLS.

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