How to Use the Universities List MCP in AutoGen

Q: How can AutoGen use Universities List?

You add searchuniversities to your list of tools. Agents then decide, through conversation, when and how best to call the function based on the user's request.

Q: Can I get data on countries with Universities List using AutoGen?

Definitely. One agent can initiate the search via searchuniversities using a country name, presenting the findings to the group for confirmation before concluding.

Q: What happens if I need data about universities with Universities List in AutoGen?

The agents will call searchuniversities, passing the university name or country. They then debate whether the results are sufficient to answer the user's query.

Achieve consensus decisions using AutoGen's multi-agent framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Universities List MCP to AutoGen

Create your Vinkius account to connect Universities List 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 Universities List with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debating Search Parameters via MCP Server

You pass `search_universities` to the Agent list. Agents can debate whether they need to search by name or country before calling the tool. This simulates a deliberation process where multiple perspectives inform the final API call. The system converges on the optimal parameters for the query, leading to more accurate and reasoned data retrieval.

Consensus-Driven Data Gathering

Multiple agents can review the results from `search_universities`. For example, a validation agent might check if the returned University names are formatted correctly, while a research agent extracts key facts. This makes the data usable right out of the box. It's about building systems that require critical discussion to reach an answer.

Structured Tool Execution with AutoGen

When defining your conversational flow, you include `search_universities` as a possible tool. The agent framework handles the schema conversion and execution automatically, feeding the results back into the conversation for debate. This makes setting up complex workflows surprisingly simple.

Setup guide

Set up Universities List 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 Universities List 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="Universities List_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Universities List 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="Universities List_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Universities List 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 Universities List. 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 Universities List 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 Universities List MCP in AutoGen

You add `search_universities` to your list of tools. Agents then decide, through conversation, when and how best to call the function based on the user's request.

The server processes global university records, specifically University names and Country information. The agents read these structured strings during their debate cycle.

Yes. If one agent needs to verify a country's universities, it calls `search_universities`. The results are then debated by other agents for completeness and accuracy.

Definitely. One agent can initiate the search via `search_universities` using a country name, presenting the findings to the group for confirmation before concluding.

The agents will call `search_universities`, passing the university name or country. They then debate whether the results are sufficient to answer the user's query.

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