How to Use the UpCloud MCP in AutoGen

Q: Can AutoGen use UpCloud for resource comparison?

Yes. Agents can compare options by running listprices and then using the result to guide a recommendation or action (like choosing between managed databases via listdatabases).

Achieve consensus-driven decisions using AutoGen and UpCloud's MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect UpCloud MCP to AutoGen

Create your Vinkius account to connect UpCloud 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 UpCloud with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

MCP Server for AutoGen Consensus Decisions

Use multiple agents to debate resource provisioning plans. One agent might check the cost via `get_billing_summary`, while another proposes a fix using `update_server`. They negotiate until they agree on the safest and most efficient change. The system can simulate complex deployments. For example, one agent identifies a need for more bandwidth, prompting another to create a load balancer (`create_load_balancer`). The discussion continues until the necessary resource is provisioned.

Collaborative Security and Network Planning

Agents can challenge each other on security best practices. A 'Security Agent' might read all existing rules using `list_firewall_rules`, prompting a 'DevOps Agent' to propose an update via `create_firewall_rule`. The debate converges on the final, approved rule set. This process handles complex network updates, like when one agent determines that a new private network is needed (`create_network`), and another verifies IP availability using `list_ips` before proceeding.

Managing State with AutoGen's MCP Server

The framework manages complex resource state transitions through deliberation. If the system needs to scale, one agent recommends cloning storage (`clone_storage`), and another executes a full `restore_storage` operation on the new copy. This consensus approach is perfect for deletions or major changes. Before calling `delete_server`, the agents might discuss impact, ensuring all dependencies are accounted for.

Setup guide

Set up UpCloud 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 UpCloud 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="UpCloud_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

The MCP Server provides discrete tools that individual agents can call. This allows the system to build a debate where different perspectives (e.g., cost, performance) drive decision-making.

Yes. Agents can compare options by running `list_prices` and then using the result to guide a recommendation or action (like choosing between managed databases via `list_databases`).

Agents can access detailed account information, including resource lists like all hosts (`list_hosts`), and billing records. The system touches several core infrastructure data types.

Yes. Because agents debate before execution, they can check resource availability (like running `list_servers`) and negotiate around potential conflicts to ensure a valid final state.

The server tracks infrastructure state changes. You can specifically retrieve account audit logs using `export_audit_logs` to give the agents full visibility into past actions.

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