mcpField
O
OpenFinance MCP Server

OpenFinance MCP Server

Local
github.com/thunderjrFinance2Updated 18w ago

About OpenFinance MCP Server

OpenFinance MCP Server is a Go application that connects to Brazil's Open Finance ecosystem through Pluggy.ai. It gives LLMs and AI agents structured access to financial data, with secrets encrypted at rest in a local SQLite database.

Key features

  1. 01Access account balances
  2. 02Retrieve transaction data
  3. 03Access investment information
  4. 04Encrypt stored credentials and tokens

Use cases

  1. 01Build AI applications using Brazilian financial data
  2. 02Review account balances and transactions
  3. 03Retrieve investment data for analysis

MCP support

The server exposes financial data from the Pluggy.ai connection to MCP clients. Access requires the relevant consents through Pluggy Connect.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

OpenFinance MCP Server

The OpenFinance MCP Server is a Go-based application that connects to the Brazilian Open Finance ecosystem through Pluggy.ai, providing secure and structured access to financial data such as account balances, transactions, and investments. It is designed to expose these resources to Large Language Models (LLMs) and other AI agents via the Model Context Protocol (MCP), facilitating the development of intelligent financial applications.

Note: Ensure to grant the necessary consents via Pluggy Connect before using.

Installation
  1. Clone the repository:
git clone https://github.com/thunderjr/openfinance-mcp-server.git
cd openfinance-mcp-server
  1. Install dependencies:
go mod tidy
  1. Build the server:
make build
  1. Use binary on your preferred MCP client (e.g. Claude Desktop):
{
  "mcpServers": {
    "openfinance-mcp-server": {
      "command": "<project_path>/bin/openfinance-mcp-server",
      "args": [],
      "env": {
        "PLUGGY_CLIENT_ID": "${PLUGGY_CLIENT_ID}",
        "PLUGGY_CLIENT_SECRET": "${PLUGGY_CLIENT_SECRET}"
      }
    }
  }
}
Credential storage

On first run the server reads PLUGGY_CLIENT_ID/PLUGGY_CLIENT_SECRET (env or ~/.config/finops/pluggy.json) once and seeds them into an encrypted SQLite database at ~/.openfinance/pluggy.db. From then on the database is the source of truth, and all secrets (credentials, cached API key, connect tokens) are sealed at rest with AES-256-GCM.

The AES master key is resolved as: $OPENFINANCE_DB_KEY (base64) → OS keychain (auto-generated on first run) → ~/.openfinance/master.key (0600 fallback). No external services are required.

Calling tools with mcporter
# Register once (stdio → built binary)
npx mcporter config add openfinance \
  --command "<project_path>/bin/openfinance-mcp-server" --scope home

npx mcporter list openfinance --schema      # show tool signatures
npx mcporter call openfinance.list_connections

🤝 Contributing

Contributions are welcome! Please fork the repository and submit a pull request with your changes.

Comments

Markdown supported

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.