About Banco Mercantil MCP
Banco Mercantil MCP connects Banco Mercantil customers and their AI agents to financial data through Brazil's Open Finance. Access requires explicit, revocable consent; queries are mainly read-only, with tools to reclassify transactions and disconnect accounts.
Key features
- 01Retrieve balances, transactions, and card bills
- 02View investments and investment transactions
- 03Review loan contracts
- 04Sync accounts and check connection status
- 05Reclassify transactions or revoke a connection
Use cases
- 01Check credit card spending this month
- 02Summarize an outstanding card bill
- 03Look up a Banco Mercantil account balance
- 04Review investment portfolio and loan information
MCP support
The MCP server exposes account, transaction, bill, investment, and loan tools to compatible MCP clients through Open Finance Brasil. Queries are read-only except for category corrections and disconnection; consent can be revoked.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://api.mcp.ai/p_mercantilclaude mcp add --transport http dir-mercantil https://api.mcp.ai/p_mercantil{"mcpServers":{"dir-mercantil":{"type":"http","url":"https://api.mcp.ai/p_mercantil"}}}Open in Cursor{"servers":{"dir-mercantil":{"type":"http","url":"https://api.mcp.ai/p_mercantil"}}}Open in VS Code{"mcpServers":{"dir-mercantil":{"type":"http","url":"https://api.mcp.ai/p_mercantil"}}}{"mcpServers":{"dir-mercantil":{"serverUrl":"https://api.mcp.ai/p_mercantil"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
25| Parameter | Type | Required | Description |
|---|---|---|---|
| keywords | array | No | |
| include_accounts | boolean | No |
Details
The maintainer has not added details yet. Check the README in the repository.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.