How to Use the Dwolla MCP in AutoGen

Q: Can AutoGen handle multi-step Dwolla onboarding?

Yes, your agents coordinate the process by running createcustomer first. Once created, another agent takes the output and triggers createcustomerfundingsource to link the bank account, ensuring a structured onboarding flow.

Q: What happens if an AutoGen agent fails a KBA verification?

If verifykba returns a failure, the security agent intercepts the conversation. It can then direct the system to trigger createdocument to request manual verification documents from the user.

Q: Where is customer SSN and routing data stored during execution?

All API calls to tools like createcustomer occur in a zero-trust, ephemeral V8 isolate sandbox. Your customer SSNs, EINs, and routing numbers are sent directly to the payments API and are never stored on Vinkius.

Deploy multi-agent AutoGen teams to debate, verify, and execute Dwolla bank transfers securely.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dwolla MCP to AutoGen

Create your Vinkius account to connect Dwolla 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 Dwolla with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run AutoGen consensus checks on high-value ACH transfers

The `initiate_transfer` tool executes ACH payments only after your agents reach consensus. Do not let a single agent initiate bank transfers unsupervised. By exposing this MCP Server to your AutoGen team, you can set up a multi-agent debate where a compliance agent checks customer verification via `get_customer` while a finance agent prepares the transaction. This consensus model minimizes risk. If the compliance agent flags that a customer has not completed KBA via `verify_kba`, it blocks the transaction, forcing the team to halt until the user's identity is fully verified.

Automate fraud detection via collaborative agent review

The `list_account_transfers` tool feeds real-time transaction data to your monitoring agents. Build an AutoGen team dedicated to monitoring suspicious activity. One agent constantly monitors transactions using this tool while another checks webhook failures via `list_events`. The team can dynamically restrict access by calling `update_funding_source` to disable a compromised bank link. This rapid, automated coordination protects your platform's financial integrity before chargebacks occur.

Coordinate complex Dwolla mass payments with AutoGen

The `initiate_mass_payment` tool coordinates high-volume vendor payouts across your agent team. Managing payouts to multiple vendors requires careful coordination. Using this MCP Server, your agents can verify vendor funding sources using `get_funding_source` before executing payments. If any vendor's account is unverified, the group pauses to initiate `verify_micro_deposits`. The agents debate the risk of proceeding, ensuring that mass payouts only execute when every destination is verified.

Setup guide

Set up Dwolla 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 Dwolla 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="Dwolla_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You set up an AssistantAgent for compliance and another for finance. Before calling `initiate_transfer`, the finance agent proposes the payload, and the compliance agent checks `get_customer` to verify identity, approving or rejecting the proposal in the chat.

Yes, your agents coordinate the process by running `create_customer` first. Once created, another agent takes the output and triggers `create_customer_funding_source` to link the bank account, ensuring a structured onboarding flow.

Use the MCP adapter to connect with the server's URL. This automatically maps all 30 financial tools, including `initiate_mass_payment`, into schema-compliant tools that your AssistantAgent can understand.

If `verify_kba` returns a failure, the security agent intercepts the conversation. It can then direct the system to trigger `create_document` to request manual verification documents from the user.

All API calls to tools like `create_customer` occur in a zero-trust, ephemeral V8 isolate sandbox. Your customer SSNs, EINs, and routing numbers are sent directly to the payments API and are never stored on Vinkius.

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