How to Use the Macaulay Library MCP in AutoGen

Deploy a team of agents with AutoGen to debate and analyze Macaulay Library archive data for complex research.

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 AutoGen

Create your Vinkius account to connect Macaulay Library to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate media search results

Assign one agent to `search_media` and another to verify the findings. They will negotiate the validity of the results before presenting you with a final answer. This prevents biased data from slipping through. You get a consensus-based result rather than a single agent's potentially flawed guess.

Automate metadata verification

Have your agents compare the data from `get_asset` against your internal requirements. If the metadata doesn't meet your standards, the agents discuss the issue and adjust their search parameters. It's like having a team of research assistants working in parallel. They handle the back-and-forth so you don't have to.

Negotiate complex research tasks

Use a multi-agent system to handle large-scale queries of the Macaulay Library. One agent focuses on the search while another manages the compute load and tool usage. They reach decisions based on the rules you set. This ensures your research stays within the limits of the API while getting the info you need.

Setup guide

Set up Macaulay Library MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Macaulay Library tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Macaulay Library_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Macaulay Library data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Macaulay Library_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Macaulay Library data")
    print(result.messages[-1].content)

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 AutoGen

Yes, that is the point. You can have one agent critique the search parameters used in `search_media` to ensure the best possible data collection.

You pass the tool list directly to the agent constructor. The adapter handles the schema so the agents know exactly how to call the functions.

Yes, you can watch the entire debate in your terminal. You see every tool call and every counter-argument as it happens.

You can set turn limits and agent constraints. This keeps your usage predictable and prevents the agents from running in circles.

The agents operate within your local process. The metadata is only shared between agents in memory, and no outside service ever sees your raw queries.

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