Compatible with every major AI agent and IDE
What is the Dwolla MCP Server?
Connect your Dwolla account to any AI agent and take full control of your payment infrastructure through natural conversation.
What you can do
- Customer Management — Create, list, and update individual or business customers directly from the chat
- Funding Sources — Link bank accounts or balances and manage them for specific customers or your main account
- Transfer Orchestration — Initiate and track transfers between funding sources with full visibility of the transaction lifecycle
- Verification Workflows — Handle micro-deposit verification to ensure secure bank account linking
- Account Insights — Retrieve organizational account details and funding source statuses instantly
How it works
- Subscribe to this server
- Enter your Dwolla Access Token and Environment (sandbox or production)
- Start managing your fintech operations from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Fintech Developers — test payment flows and verify customer data without leaving the IDE
- Operations Teams — monitor transfer statuses and manage customer records through simple queries
- Product Managers — audit funding sources and account balances during development cycles
Built-in capabilities (30)
Cancel a pending transfer
Create a beneficial owner for a business customer
Create a new customer
Create a funding source for a customer
Create a document for a customer
Create a funding source
Create a label for a customer
Create a webhook subscription
Retrieve Dwolla account details
Retrieve a customer
Retrieve a document
Retrieve an event
Retrieve a funding source
Retrieve a mass payment
Retrieve a transfer
Initiate a KBA session for a customer
Initiate a mass payment
Requires HAL _links in the payload. Initiate a transfer
List funding sources for an account
List transfers for an account
List beneficial owners for a customer
List or search customers
List events
List labels for a customer
List webhook subscriptions
Retry a webhook
Update a customer
g., passing { removed: true }). Update or remove a funding source
Verify KBA answers
Verify micro-deposits for a funding source
Why Cursor?
Cursor's Agent mode turns Dwolla into an in-editor superpower. Ask Cursor to generate code using live data from Dwolla and it fetches, processes, and writes. all in a single agentic loop. 30 tools appear alongside file editing and terminal access, creating a unified development environment grounded in real-time information.
- —
Agent mode turns Cursor into an autonomous coding assistant that can read files, run commands, and call MCP tools without switching context
- —
Cursor's Composer feature can generate entire files using real-time data fetched through MCP. no copy-pasting from external dashboards
- —
MCP tools appear alongside built-in tools like file reading and terminal access, creating a unified agentic environment
- —
VS Code extension compatibility means your existing workflow, keybindings, and extensions all work alongside MCP tools
Dwolla in Cursor
Dwolla and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Dwolla to Cursor through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Dwolla in Cursor
The Dwolla MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 30 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Cursor only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Dwolla for Cursor
Every tool call from Cursor to the Dwolla MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How do I verify a bank account using micro-deposits?
Use the verify_micro_deposits tool by providing the Funding Source ID and the two deposit amounts. This ensures the bank account is active and owned by the customer.
Can I create a new customer directly through the AI?
Yes! Use the create_customer tool with a JSON payload containing the customer's details like firstName, lastName, and email.
How can I see the history of transfers for my organization?
You can use the list_account_transfers tool with your Account ID to retrieve all recent and past fund movements associated with your Dwolla account.
What is Agent mode and why does it matter for MCP?
Agent mode is Cursor's autonomous execution mode where the AI can perform multi-step tasks: reading files, editing code, running terminal commands, and calling MCP tools. Without Agent mode, Cursor operates in a simpler ask-and-answer mode that doesn't support tool calling. Always ensure you're in Agent mode when working with MCP servers.
Where does Cursor store MCP configuration?
Cursor looks for MCP server configurations in a mcp.json file. You can configure servers at the project level (.cursor/mcp.json in your project root) or globally (~/.cursor/mcp.json). Project-level configs take precedence.
Can Cursor use MCP tools in inline edits?
No. MCP tools are only available in Agent mode through the chat panel. Inline completions and Tab suggestions do not trigger MCP tool calls. This is by design. tool calls require user visibility and approval.
How do I verify MCP tools are loaded?
Open Settings → Features → MCP and look for your server name. A green indicator means the server is connected. You can also check Agent mode's available tools by clicking the tools dropdown in the chat panel.
Tools not appearing in Cursor
Ensure you are in Agent mode (not Ask mode). MCP tools only work in Agent mode.
Server shows as disconnected
Check Settings → Features → MCP and verify the server status. Try clicking the refresh button.
Explore More MCP Servers
View all →
Hyperbrowser (Web Infra for AI)
10 toolsCloud browsers for AI agents via Hyperbrowser — manage sessions, scrape pages, and extract structured data.

GetStream
23 toolsBuild and manage scalable activity feeds and social networks. Manage activities, feeds, and follower relationships directly through your AI agent.

OpenAQ
9 toolsAccess global air quality data — monitor PM2.5, O3, NO2 levels and track pollution via AI.

Metatext
10 toolsNo-code NLP and AI model management via Metatext — run inference and manage datasets.
