How to Use the Brankas MCP in AutoGen

Q: How do agents handle a failed transfer status?

If gettransferstatus returns a failed state, the execution agent reports the error back to the group. The agents then discuss alternative routing options, like trying intrabanktransfer instead.

Q: How does AutoGen secure my bank identity data?

All identity details retrieved via getidentities are processed in ephemeral memory. The host sandbox uses hardware-level isolation to prevent any bank credentials or customer profiles from leaking between agent sessions.

Let your AutoGen agents debate and approve payouts safely using the Brankas open finance tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Brankas MCP to AutoGen

Create your Vinkius account to connect Brankas 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 Brankas with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-driven payout approval in AutoGen

Coordinate payouts using `inter_bank_transfer` after your agents debate the transfer terms. Set up a system where multiple agents debate a transfer using this MCP server. The agents negotiate the transfer route based on cost and speed. Once they reach consensus, the execution agent initiates the payout and monitors the progress using `get_transfer_status`.

Multi-agent checkout validation

Create payment sessions using `create_checkout` while a compliance agent calls `get_identities` to verify the buyer's bank registration. This multi-agent setup prevents unauthorized transactions by forcing a debate. If the compliance agent flags a mismatch, the conversation halts. No money changes hands until both agents agree that the customer identity matches the transaction parameters.

Automate treasury audits with this MCP Server

Pull bank statement records via `get_statement` to let your agents audit your books through conversation. An auditing agent compares the statement with internal invoices while a supervisor agent reviews the results. This MCP setup allows your agents to collaborate on complex financial reconciliation. Instead of a single script running blindly, the agents verify each transaction status with `get_transaction` and discuss anomalies.

Setup guide

Set up Brankas 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 Brankas 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="Brankas_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Yes. You can instruct one agent to propose a budget while another uses `get_balance` to verify if the Brankas account can support the payout, deciding on the transfer amount through debate.

The MCP tool adapter handles the schema conversion automatically. It translates the Brankas API parameters into JSON schemas that your AutoGen agents can understand and execute.

Yes. You can register multiple MCP servers with your AutoGen environment. This lets your agents query Brankas for bank data while simultaneously calling a separate database server to log the transaction.

If `get_transfer_status` returns a failed state, the execution agent reports the error back to the group. The agents then discuss alternative routing options, like trying `intra_bank_transfer` instead.

All identity details retrieved via `get_identities` are processed in ephemeral memory. The host sandbox uses hardware-level isolation to prevent any bank credentials or customer profiles from leaking between agent sessions.

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