douglas-banco-mcp
mcpsmithery# Banco MCP — Open Finance Brasil Conecte 30+ bancos brasileiros (Itaú, Nubank, Bradesco, Santander, Inter, Banco do Brasil, Caixa, C6 e mais) ao Claude, Cursor e agentes de IA via **Open Finance**, regulado pelo Banco Central. Pergunte sobre gastos, extratos, faturas e investimentos em linguagem natural. - 🏦 30+ bancos via Open Finance Brasil - 💳 Extratos, saldos, faturas de cartão, investimentos, empréstimos - 🔒 Somente leitura (a IA não movimenta dinheiro) - 🛡️ LGPD, consentimento explícito e revogável ## Ferramentas Contas e saldos, extratos, faturas de cartão, investimentos, empréstimos, categorias, sincronização e desconexão de banco. Funciona em qualquer cliente MCP. Servidor remoto: `https://api.mcp.ai/banco`
By Smithery | 51 findings | Scanned 7/5/2026 | tooltrust-scanner/v0.3.19
Risk Summary
Safe With Normal ControlsDep Visibility is the main signal, but overall risk remains within an acceptable range.
Potential impact: This finding indicates the tool should be reviewed before it is trusted.
Recommended action: No high-risk findings were detected in this scan, but you should still apply least-privilege defaults and rescan after changes.
Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.
Security Findings (51)
tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration
openfinance_search_bank_connectorsopenfinance_list_connectionsopenfinance_get_item_statusopenfinance_list_transactionsopenfinance_list_credit_card_billsopenfinance_list_investment_transactionsopenfinance_list_loansopenfinance_force_syncopenfinance_get_account_balanceopenfinance_disconnect_bankconnectmarketplaceFix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.
marketplace:input schema exposes 13 properties (threshold: 10)
Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
declared capabilities: network access
openfinance_search_bank_connectorsopenfinance_list_connectionsopenfinance_list_loansopenfinance_get_account_balanceopenfinance_disconnect_bankconnectdeclared capabilities: code/command execution
openfinance_get_item_statusopenfinance_list_credit_card_billsopenfinance_force_syncdeclared capabilities: code/command execution, database access
openfinance_list_transactionsdeclared capabilities: code/command execution, HTTP requests
openfinance_list_investment_transactionsdeclared capabilities: filesystem access
openfinance_update_transaction_categorydeclared capabilities: code/command execution, filesystem access
marketplaceFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.
openfinance_search_bank_connectorsopenfinance_list_connectionsopenfinance_get_item_statusopenfinance_provider_statusopenfinance_list_accountsopenfinance_list_transactionsopenfinance_list_transactions_by_itemopenfinance_list_credit_card_billsopenfinance_list_investmentsopenfinance_list_investment_transactionsopenfinance_list_loansopenfinance_force_syncopenfinance_get_account_balanceopenfinance_get_accounts_detailopenfinance_get_credit_card_billopenfinance_list_categoriesopenfinance_update_transaction_categoryopenfinance_disconnect_bankshow_versionreport_bugconnecttoolkit_infomarketplaceauthenticateFix: Review and remediate the identified issue.
authenticate:input parameter "token" accepts a credential (informational; not evidence of insecure handling)
Fix: Avoid accepting raw credentials as input parameters. Use secret managers (e.g. 1Password CLI, AWS Secrets Manager) and ensure credentials are never logged or stored in agent traces.
Scan this tool yourself
Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.
Install once, then scan any MCP server:
$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash$ tooltrust-scanner scan --server "npx -y douglas-banco-mcp"Adjust the package name if your npm registry name differs from the tool ID. View source
Add badge to your README
Copy this Markdown to show your ToolTrust grade on GitHub.
[](https://github.com/AgentSafe-AI/tooltrust-directory)