How to Use the NachoNacho MCP in AutoGen

Q: How do I configure the NachoNacho MCP Server in AutoGen?

Install the autogen-extmcp package. Use mcpservertools with a StreamableHttpServerParams URL, and pass the resulting tools to your AssistantAgent.

Q: How do the agents handle schema conversions?

The McpToolAdapter automatically translates the server schemas into formats the agents understand. You write zero custom parsing logic.

AutoGen agents use this MCP Server to debate and manage your SaaS spend autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NachoNacho MCP to AutoGen

Create your Vinkius account to connect NachoNacho 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 NachoNacho with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Procurement Debates

`create_card` becomes the final step of an automated negotiation between your AutoGen agents. A developer agent requests a new software tool. The finance agent pushes back, demanding justification and checking current budgets via `list_balances`. They deliberate until consensus is reached. Once the finance agent approves the request, it executes the tool call to provision a virtual card. The entire approval workflow happens without human intervention, governed strictly by the system prompts you assigned to each persona.

Autonomous SaaS Auditing

`list_transactions` and `list_subscriptions` give your auditor agents the raw data they need to hunt down wasted spend. One agent pulls the transaction logs. A second agent analyzes the data for duplicate subscriptions across different departments. If they find overlap, a third agent steps in to take action. It triggers `freeze_card` on the redundant account. You watch the terminal as the agents discuss the anomaly, agree on the remediation, and execute the API call.

NachoNacho MCP Server Fleet Management

`list_cards` and `update_card` allow your AutoGen framework to manage hundreds of virtual cards dynamically. A monitoring agent continuously polls the active card list. If it detects a card nearing its monthly limit, it alerts a manager agent. The manager agent evaluates the vendor's importance. If the tool is mission-critical, it automatically updates the card limit to prevent a failed payment. The agents handle the operational friction while you focus on higher-level strategy.

Setup guide

Set up NachoNacho 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 NachoNacho 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="NachoNacho_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install the `autogen-ext[mcp]` package. Use `mcp_server_tools` with a `StreamableHttpServerParams` URL, and pass the resulting tools to your `AssistantAgent`.

Yes. You distribute the tools across different agents. The finance agent gets write access, while the auditor agent only gets read access.

The `McpToolAdapter` automatically translates the server schemas into formats the agents understand. You write zero custom parsing logic.

That depends entirely on your configuration. You require human-in-the-loop approval before any agent executes a destructive action.

The MCP execution handles sensitive virtual card limits and active subscription metadata. Vinkius isolates the environment completely, ensuring that agent deliberations and tool outputs never leak across tenant boundaries.

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