How to Use the ncScale MCP in AutoGen

Q: How do I configure AutoGen with the ncScale MCP Server?

Install the autogen-extmcp package. Initialize mcpservertools with your HTTP transport parameters. Pass the resulting tool list to your AssistantAgent constructor.

Let agents debate system health. AutoGen uses ncScale to triage no-code failures via consensus.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ncScale MCP to AutoGen

Create your Vinkius account to connect ncScale 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 ncScale with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Triage for ncScale MCP Server

The ncScale MCP Server gives AutoGen agents the data they need to triage no-code failures collaboratively. You set up a DevOps agent and a Database agent, then hand them the tool set. When an error spikes, the DevOps agent calls `list_alerts` to check the severity. The Database agent simultaneously runs `get_node` to inspect the failing integration. They debate the root cause in a shared chat until they agree on a fix.

Correlate Logs Through Conversation

One agent pulls the raw error traces using `list_logs` while another reviews support requests via `list_tickets`. Finding the origin of a cascading failure requires different perspectives. They cross-reference their findings automatically. If the log agent sees a timeout and the support agent sees user complaints about a specific dashboard, they merge the data. You get a finalized incident report without reading a single JSON payload manually.

Audit Dashboards and Workspaces

Assign a Security agent to query `get_workspace_info` and `list_users` to automate your infrastructure audits. It checks who has access to what without requiring human oversight. An Optimization agent looks at `list_dashboards` to see which views are actually being used. The MCP Server handles the data extraction while your agents discuss whether dormant integrations should be removed. You just review their final recommendation and approve the cleanup.

Setup guide

Set up ncScale 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 ncScale 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="ncScale_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install the `autogen-ext[mcp]` package. Initialize `mcp_server_tools` with your HTTP transport parameters. Pass the resulting tool list to your `AssistantAgent` constructor.

Yes. Once you provide the tools, the agents decide when to call them. A monitoring agent might poll `list_alerts` every ten minutes and wake up the triage agent if it finds a critical error.

The framework handles the state internally. When one agent executes `list_integrations`, the resulting JSON is injected into the shared conversation history. Every other agent in that chat can read and analyze the output.

It can burn tokens quickly if you are not careful. You should instruct the fetching agent to summarize the output of `list_logs` before passing it to the reasoning agents.

The agents read raw infrastructure states, including active alerts, dashboard configurations, and user lists. Vinkius guarantees secure execution by running the MCP connection in an isolated, zero-trust environment. No operational data is stored on our servers after the connection drops.

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