How to Use the Flystack MCP in AutoGen

Q: Can AutoGen agents coordinate to analyze Flystack cluster metrics?

Yes, one agent can fetch the metrics using getclustermetrics and share the raw JSON with a specialized analyst agent. They work together to pinpoint performance bottlenecks.

Let your AutoGen agents debate and diagnose Flystack deployment health and cluster metrics in real time.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Flystack MCP to AutoGen

Create your Vinkius account to connect Flystack 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 Flystack with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-driven cluster diagnostics in AutoGen

Set up a multi-agent debate to troubleshoot production incidents. One agent queries `get_cluster_metrics` to check for resource spikes, while another pulls config metadata using `get_deployment_details`. The agents compare notes inside the AutoGen conversation. They argue over whether a memory leak or a bad environment variable caused the crash, arriving at a consensus before showing you the solution.

Automated infrastructure status checks

Your coordinator agent can run `check_api_status` to confirm the API is up before starting a deployment audit. If the status is red, the agent halts the conversation and alerts your team. Once verified green, the agent instructs sub-agents to run `list_flystack_clusters` to map the active environment. This keeps your automated workflows from wasting tokens on dead endpoints.

Collaborative deployment auditing

Assign different agents to watch different parts of your stack. A performance agent monitors metrics, while a compliance agent reviews active configurations fetched via `list_flystack_deployments`. When a new deployment goes live, the compliance agent checks its specs against your policies. If there is a mismatch, it flags the issue to the group, using live data to back up its claim.

Setup guide

Set up Flystack 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 Flystack 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="Flystack_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Use the AutoGen MCP extension to load the tools. Pass the adapter-wrapped tools directly to your AssistantAgent constructor so they can invoke `list_flystack_deployments` during conversations.

Yes, one agent can fetch the metrics using `get_cluster_metrics` and share the raw JSON with a specialized analyst agent. They work together to pinpoint performance bottlenecks.

The MCP adapter returns the error directly to the active agent. The agent then discusses the failure with the group, perhaps deciding to run `check_api_status` to see if the control plane went down.

The Streamable HTTP transport is highly recommended for multi-agent setups. It handles concurrent requests smoothly when multiple agents are querying different endpoints at the same time.

Your cluster performance data and deployment metrics stay strictly within your local AutoGen environment. The MCP server runs in an isolated sandbox, ensuring no telemetry is leaked or stored.

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