How to Use the Dwolla MCP in LangChain

Q: How do I pass Dwolla HAL links between tools in a LangChain run?

LangChain agents handle this by passing the output of getcustomer or createcustomer directly into the input payload of initiatetransfer. Since the MCP Server outputs JSON containing these HAL links, your ReAct agent extracts and maps them to the next tool in the chain automatically.

Q: Can I trace Dwolla API rate limits inside a LangChain run?

Yes, every call made by the LangChain agent to tools like listaccounttransfers or getfundingsource is tracked. LangSmith captures the metadata, helping you monitor how close your agent is getting to Dwolla's API limits.

Q: How does this server secure sensitive financial data like SSNs and bank routing numbers?

All sensitive payloads processed by tools like createcustomer run inside an isolated, zero-trust V8 sandbox. No routing numbers, SSNs, or KYC documents are stored on Vinkius servers, keeping your customer data fully secure.

Run multi-step ACH payment chains and customer verification pipelines directly within your LangChain agent.

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 LangChain

Create your Vinkius account to connect Dwolla to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain KYC verification with instant funding source setup

The `create_customer` tool allows your agent to register new users and kick off onboarding chains. Your agent first triggers this tool to register the user, then immediately sets up the bank link with `create_customer_funding_source`. If LangChain detects a business profile, it branches the chain to call `create_beneficial_owner` before initiating any financial moves. This multi-step pipeline passes outputs directly from one tool to the next. You don't write glue code. Your agent evaluates the status of each step, handles KBA questions via `initiate_kba`, and only proceeds to `verify_kba` when the step is ready.

Trace Dwolla MCP Server transfers step-by-step in LangSmith

The `initiate_transfer` tool handles ACH bank payments directly within your agent's execution path. Debugging bank transfers is notoriously difficult when you don't know why a transaction stalled. By connecting this MCP Server to your LangChain setup, every call to this tool or `cancel_transfer` gets logged in LangSmith. This deep visibility lets you monitor latency and token usage for complex financial operations. If a mass payout fails during `initiate_mass_payment`, you can inspect the tool inputs in your LangSmith trace to fix payload formatting errors on the spot.

Automate failed webhook retries inside LangGraph

The `list_events` tool monitors system webhooks to trigger automated recovery flows. When a webhook flags a transfer failure, the graph triggers this tool to pinpoint the breakdown. Your agent then decides whether to run `retry_webhook` or update the bank details using `update_funding_source`. This loop keeps your ledger accurate without hardcoding retry policies. The LangChain agent reads the event history via `get_event`, assesses the failure reason, and executes the correct recovery path dynamically.

Setup guide

Set up Dwolla MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Dwolla tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "dwolla-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Dwolla transactions"
    })
    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 LangChain

LangChain agents handle this by passing the output of `get_customer` or `create_customer` directly into the input payload of `initiate_transfer`. Since the MCP Server outputs JSON containing these HAL links, your ReAct agent extracts and maps them to the next tool in the chain automatically.

Yes, every call made by the LangChain agent to tools like `list_account_transfers` or `get_funding_source` is tracked. LangSmith captures the metadata, helping you monitor how close your agent is getting to Dwolla's API limits.

You initialize the client with the Dwolla endpoint alongside your other services. This allows your LangChain agent to query a database for user details and immediately use those details to run `create_customer` on this server.

You should set up a stateful chain. The agent initiates the link, and once the user provides the deposit amounts, LangChain calls `verify_micro_deposits` to complete the verification before allowing any transfers.

All sensitive payloads processed by tools like `create_customer` run inside an isolated, zero-trust V8 sandbox. No routing numbers, SSNs, or KYC documents are stored on Vinkius servers, keeping your customer data fully secure.

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