Open Finance Brasil MCP. Balance accounts, track debt, and view investments.
Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Open Finance Brasil connects your AI agent to comprehensive Brazilian financial data. Access everything from checking real-time account balances (`get_accounts`) and transaction history (`get_transactions`) to tracking credit card limits, investment portfolios, and loan details.
It gives your agent a full view of the customer's financial standing.
What your AI agents can do
Get accounts
Retrieves a list of payment accounts, showing the type, agency, number, and current balance for each.
Get credit card bills
Fetches outstanding credit card bills after you provide a specific Credit Card Account ID.
Get credit cards
Gets all linked credit card accounts, returning the brand and current limits (total, available, used).
The agent lists all associated payment accounts, providing the account type, agency, number, and current available balance.
You pull credit card accounts and their limits (total, used, available), or fetch specific outstanding bills for a given card ID.
The agent retrieves detailed transaction records for any specified account ID to analyze spending patterns.
It pulls basic customer identification details, including name, CPF, and address, which is necessary context for all other queries.
The agent gathers data on various assets like funds, CDBs, and treasury holdings to build an investment picture.
You pull records for financing agreements, including loans, vehicle financing, or real estate mortgages.
Ask AI about this MCP
Supported MCP Clients
Open Finance Brasil: 7 Tools for Full Financial View
Use these seven tools to allow your AI client to run complex, multi-step queries against a customer's complete financial profile.
019d75e7get accounts
Retrieves a list of payment accounts, showing the type, agency, number, and current balance for each.
019d75e7get credit card bills
Fetches outstanding credit card bills after you provide a specific Credit Card Account ID.
019d75e7get credit cards
Gets all linked credit card accounts, returning the brand and current limits (total, available, used).
019d75e7get customer data
Retrieves basic personal identification information for the customer: Name, CPF, and Address.
019d75e7get financing
Gets details on long-term contracts, including loans, vehicle financing, or real estate mortgages.
019d75e7get investments
Retrieves the portfolio holdings and values for various investments like funds, CDBs, and treasury bonds.
019d75e7get transactions
Pulls a history of transactions after you specify an Account ID from `get_accounts`.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Open Finance Brasil, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
Listen up. You don't gotta log into seven different banking portals just to get a full picture of someone's money. This server connects your AI agent directly to core Brazilian financial sources, giving it access to everything from basic identity checks to investment portfolio values. It’s the single data pipeline you need.
To start, your agent first pulls the basics: customer identification details like their Name, CPF, and Address using get_customer_data. This context is critical for every other query you run against the system.
When it comes to liquid cash and spending, your agent can list all associated payment accounts. Using get_accounts, it pulls out the account type, agency, number, and what's currently sitting in that balance. If you wanna know how money moves through those accounts, you run get_transactions—you just gotta feed it an Account ID pulled from the previous step to get a full history of spending patterns.
Tracking debt is where this thing really shines. You can pull all linked credit card accounts with get_credit_cards, which gives you the brand, and the total, used, and available limits across the board. If you need specifics on what's due right now, running get_credit_card_bills lets your agent fetch outstanding bills after you provide a specific Credit Card Account ID.
For bigger picture debt—the stuff that lasts longer than a month—you use get_financing. This tool pulls records for long-term contracts, covering everything from auto loans to mortgages and other major financing agreements. It gives the full scope of their committed liabilities.
Then there's the wealth side of things. You can build out a complete investment profile using get_investments, which gathers data on various assets like funds, CDBs, or treasury bonds, showing you what they actually own and how much it's worth. This is your holistic view of their net worth.
By chaining these tools together—starting with identity, getting the current balances from get_accounts, reviewing spending history with get_transactions, checking credit limits via get_credit_cards while also pulling specific bills using get_credit_card_bills, understanding long-term debt through get_financing, and wrapping it all up with asset values from get_investments—your agent builds a complete, multi-layered financial profile.
It’s not just data retrieval; you're performing full financial analysis right in the prompt. You don't need to juggle multiple API keys or write complex SQL queries. Your AI client handles it all through one clean protocol.
How Open Finance Brasil MCP Works
- 1 Start by invoking
get_customer_datato establish the user's identity (Name, CPF). This data acts as context for all subsequent calls. - 2 The agent then executes a sequence of tools—for example, calling
get_accountsand passing the resulting Account IDs intoget_transactions. The system compiles these disparate results. - 3 You receive a single, synthesized output stream that contains all requested balances, transaction lists, credit card limits, and investment values, ready for your AI client to analyze.
The bottom line is: Your agent runs the multi-step financial check using natural language prompts, handles the API calling sequence, and returns a unified data object instead of requiring multiple manual tool calls.
Who Is Open Finance Brasil MCP For?
The fintech developer building compliance tools who needs to verify a customer's entire financial profile in one go. It’s for the loan officer who can't afford to check five different dashboards and the wealth manager who needs real-time asset visibility.
Builds applications that require a unified view of financial data, using tools like get_transactions and cross-referencing them with get_accounts.
Determines an applicant's total debt load by coordinating calls between get_credit_cards, get_financing, and checking available balances via get_accounts.
Verifies customer identity using get_customer_data before accessing sensitive asset information from get_investments or loan details from get_financing.
What Changes When You Connect
- Get real-time balances using
get_accounts. You instantly see the current status of all payment accounts without needing to check multiple banking apps. - Assess total risk by comparing limits. Combining
get_credit_cardswithget_financinggives a clear, unified picture of both revolving and installment debt. - Analyze spending patterns immediately. Calling
get_transactionsfor an account ID lets you see the flow of money that led to a specific balance drop. - Build a full profile quickly. Starting with
get_customer_dataprovides necessary identity context before running any financial queries, improving data integrity. - Track wealth growth and debt simultaneously. You get two sides of the ledger: assets from
get_investments, balanced against obligations fromget_credit_card_bills.
Real-World Use Cases
Processing a New Loan Application
A loan officer needs to qualify a client. Instead of asking the user for statements, they prompt their agent: 'Run full profile check.' The agent runs get_customer_data -> get_accounts -> get_credit_cards and get_financing. The output is an immediate risk assessment.
Identifying Spending Anomalies
A user suspects unauthorized charges. They prompt the agent to run get_transactions for their primary account ID, then use that data point to compare against known bills retrieved via get_credit_card_bills. The discrepancy is flagged instantly.
Calculating Net Worth
A wealth manager needs a client's total net worth. They instruct the agent to run get_accounts (liquidity), get_investments (assets), and get_financing (liabilities). The combined result is the true, current net worth figure.
Onboarding a New Corporate Client
A compliance team needs to verify company leadership. They first run get_customer_data, then pull all associated corporate accounts using get_accounts. This verifies the legal identity and operational financial standing simultaneously.
The Tradeoffs
Only checking the balance
User only runs get_accounts and thinks they know how healthy the finances are. They miss knowing if their spending is covered by available credit or if they have looming loan payments.
→
Always couple get_accounts with get_credit_cards and get_financing. Checking balances without reviewing debt limits gives an incomplete financial story.
Skipping identity verification
Running complex queries like get_transactions or get_investments without first calling get_customer_data. The AI agent might fail to link the data correctly, returning generic or unverified records.
→
Always start by running get_customer_data as the foundational step. It provides the necessary context (Name/CPF) for every subsequent query.
Assuming all money is liquid
Looking only at balances from get_accounts. This ignores large amounts of capital tied up in long-term assets or investments.
→
To get a full picture, you must include both get_investments and get_financing alongside the basic account balance to calculate true accessible capital.
When It Fits, When It Doesn't
Use this server if your goal is synthesis. If you need to know how money flows—the relationship between a transaction (get_transactions), a spending limit (get_credit_cards), and the underlying asset balance (get_accounts)—this is necessary. You are building a multi-step analysis.
Don't use this if your goal is simple lookup. If you just need to know, 'What was my last transaction?' or 'What is my current loan balance?', running multiple tools is overkill. In those cases, calling the single specific tool (get_transactions or get_financing) directly is faster and cleaner.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Open Finance Brasil. 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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 7 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Gathering a full financial picture used to involve logging into five different portals.
You open your browser. First, you check the bank's online portal for liquid cash balances (`get_accounts`). Then, you switch tabs to the credit card issuer site to see available limits and pending bills. Next, you go to the investment platform to pull your fund performance data. Finally, you log into the loan servicer just to confirm mortgage details.
With this MCP server, your agent handles all of that complexity in one prompt. You ask: 'What is my total debt load versus my current liquid assets?' The AI client runs `get_accounts`, `get_credit_cards`, and `get_financing` automatically, returning a single report without you touching another tab.
Open Finance Brasil MCP Server: Unified financial analysis.
Manual cross-referencing is tedious. You must compare the transaction dates from your bank statement against the investment purchase records and then manually reconcile that against the credit card billing cycle to spot discrepancies.
The agent abstracts this complexity away. It executes the necessary tool calls in sequence—for instance, linking a specific `get_transactions` record to an account ID used by `get_accounts`—and presents you with validated, linked data.
Common Questions About Open Finance Brasil MCP
How do I get my spending history using get_transactions? +
You must first call get_accounts to find the specific Account ID. Then, pass that ID into get_transactions. The tool retrieves a detailed list of all transactions for that account.
Does Open Finance Brasil MCP Server show my investment growth? +
Yes. Use get_investments to pull data on funds, CDBs, and treasury holdings to see your current portfolio value.
I need to check my credit card limits; which tool do I use? get_credit_cards? +
The get_credit_cards tool retrieves all linked cards. It gives you the total, available, and used limit for each brand.
How can I check my current loan status? +
Run the get_financing tool. This returns specific details on any active loans or mortgages you have taken out.
What information do I need to provide when calling get_customer_data? +
You must supply the customer's CPF, name, and current address. The tool returns basic identification info, which confirms your agent has correctly scoped the data to that specific person.
If I use get_credit_card_bills but don't have a valid Credit Card Account ID, what happens? +
The process fails because it requires an explicit Credit Card Account ID. Your agent needs to run get_credit_cards first to retrieve the correct identifier before requesting bills.
How do I make sure I pull all my accounts and balances using get_accounts? +
The tool lists payment account details, including type, agency, number, and balance. If you have many accounts, your agent will likely need to run the function multiple times or handle pagination to retrieve every entry.
Can I use get_investments data to compare against my checking balances from get_accounts? +
Yes, you can compare them. You call get_accounts for liquid cash and then run get_investments to see the value of funds like CDBs or treasury holdings.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
X Ads (Twitter)
Manage your X Ads campaigns — audit accounts, line items, and analytics via AI.
Anthropic Alternative
Access Claude models via Anthropic API — send messages, count tokens, manage batches and discover models from any AI agent.
Tesla Fleet API
Physical actuator proxy mapping explicitly native commands evaluating telemetry tracking active Tesla vehicles cleanly.
You might also like
Clearout
Verify email addresses in bulk before sending campaigns to protect your sender reputation and improve deliverability rates.
EPO Open Patent Services
Search global patents — audit bibliographic and legal data via AI.
Vibrato
Manage secrets and environment variables securely across your development and deployment pipeline with encrypted vaults.