How to Use the Macaulay Library MCP in Mastra AI

Q: How can I use Mastra AI to build a reliable data sync with the Macaulay Library?

Create a Mastra AI workflow that periodically calls the getrecentmedia tool. Use the results to update your database, and rely on Mastra's built-in retry logic to handle any temporary network or API issues, ensuring your sync process doesn't fail.

Q: Can I filter assets from the Macaulay Library by quality using Mastra AI?

Yes. After using searchmedia, have your Mastra AI agent loop through the asset IDs and call getasset on each one. Then, use a conditional branch in your workflow to only process assets that meet your quality rating criteria.

Q: Does this MCP server work with Mastra's human-in-the-loop features?

Absolutely. You can configure your agent with requireToolApproval. When the agent wants to call getasset on a large batch of IDs from a search, it will pause and wait for your confirmation before proceeding with the metadata requests.

Build resilient data pipelines with Mastra AI. Ingest wildlife media metadata from the world's largest archive with automatic retries and error handling.

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 Mastra AI

Create your Vinkius account to connect Macaulay Library to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create Robust Ingestion Workflows

The `search_media` tool is your entry point for finding specific assets. You can build a Mastra AI workflow that searches for all audio recordings of a species, then passes the list of asset IDs to the next step for processing. Here’s the thing: APIs can be flaky. Mastra AI's engine automatically retries the `search_media` call with exponential backoff if the Macaulay Library API is temporarily unavailable. Your workflow doesn't crash; it just waits and tries again.

Process Metadata with Conditional Logic

After finding assets, your workflow uses `get_asset` to pull down the full metadata for each one. This includes location, date, quality ratings, and more. It's everything you need for serious data analysis. Your Mastra AI agent can use conditional logic on this data. For example: IF the audio quality rating from `get_asset` is below 'C', THEN discard the asset. ELSE, IF the location is within a target research area, THEN add it to a database. This lets you build sophisticated, automated data-cleaning pipelines.

Build a Resilient Mastra AI Data Feed

Use the `get_recent_media` tool to create a workflow that constantly checks for new data. This is how you keep a local database or research collection in sync with the main Macaulay Library archive without manual intervention. This MCP Server is your source, and Mastra AI provides the reliability. If a call to `get_recent_media` returns an empty list, your workflow can simply pause and wait before trying again, preventing unnecessary processing and API calls.

Setup guide

Set up Macaulay Library MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Macaulay Library tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "macaulay-library-mcp-client",
  servers: {
    "macaulay-library-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Macaulay Library Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Macaulay Library tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Macaulay Library transactions"
);
console.log(result.text);

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 Mastra AI

Create a Mastra AI workflow that periodically calls the `get_recent_media` tool. Use the results to update your database, and rely on Mastra's built-in retry logic to handle any temporary network or API issues, ensuring your sync process doesn't fail.

Your Mastra AI workflow won't fail. You can add a conditional step that checks if the asset list is empty. If it is, the workflow can either terminate gracefully, log a message, or even try a different search using broader criteria.

Yes. After using `search_media`, have your Mastra AI agent loop through the asset IDs and call `get_asset` on each one. Then, use a conditional branch in your workflow to only process assets that meet your quality rating criteria.

Absolutely. You can configure your agent with `requireToolApproval`. When the agent wants to call `get_asset` on a large batch of IDs from a search, it will pause and wait for your confirmation before proceeding with the metadata requests.

Mastra AI's client processes data in-memory for the duration of a workflow step. It fetches asset metadata—like species, date, and location from `get_asset`—uses it for your logic, and then discards it. The server connection is handled via your Vinkius endpoint token, keeping credentials isolated.

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