How to Use the Stark Bank MCP in AutoGen

Q: Can AutoGen handle multiple types of outgoing payments?

Yes. The framework can involve agents calling both starkcreatetransfer for payroll and also using the card creation tool, starkcreatecorporatecard, to manage expense flows simultaneously.

Achieve consensus decisions with AutoGen using Stark Bank tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Stark Bank MCP to AutoGen

Create your Vinkius account to connect Stark Bank to AutoGen — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Stark Bank with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Simulating Payment Debates (AutoGen)

Use multiple agents to debate payment strategy. One agent can call `stark_get_balance` and declare that funds are low, while another calls `stark_create_boleto`, proposing a slow receivables method. The third might argue for immediate action via `stark_create_pix_charge`. This simulates consensus-driven decision making when the answer isn't obvious.

Audit Workflow Negotiation (MCP Server)

An auditing agent can check historical data using `stark_list_boletos` and compare it against a performance agent's view of current outgoing payments via `stark_list_transfers`. They debate if the payment schedule is compliant or too slow. The MCP Server provides the facts—the logs—that force the agents to argue based on real data.

Card Policy Enforcement (AutoGen)

You can set up a security agent that flags risks associated with `stark_create_corporate_card` usage. A performance agent might push for higher limits, forcing the agents to negotiate policy changes based on actual spending reports from `stark_list_pix_charges`. This is ideal for complex governance where competing perspectives must converge.

Setup guide

Set up Stark Bank 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 Stark Bank 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="Stark Bank_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

It allows agents to debate strategies. For example, they might argue whether to send a payment via `stark_create_transfer` or wait and process it as an invoice using `stark_create_boleto`, based on defined risk profiles.

Yes. The framework can involve agents calling both `stark_create_transfer` for payroll and also using the card creation tool, `stark_create_corporate_card`, to manage expense flows simultaneously.

The MCP Server gives agents access to all core financial tools. They can run full cycles: check balance (`stark_get_balance`), issue charges (`stark_create_pix_charge`), and then reconcile the results.

It lets agents track payments by having them compare data from `stark_list_transfers` (for outgoing funds) against `stark_list_pix_charges` (for incoming debits), forcing a reconciliation debate.

The server touches all financial transaction data, including detailed raw cash flow statements and the status of issued Boletos.

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